[HN Gopher] Show HN: Executable Markdown files with Unix pipes
___________________________________________________________________
Show HN: Executable Markdown files with Unix pipes
I wanted to run markdown files like shell scripts. So I built an
open source tool that lets you use a shebang to pipe them through
Claude Code with full stdin/stdout support. task.md:
#!/usr/bin/env claude-run Analyze this codebase and
summarize the architecture. Then: chmod +x
task.md ./task.md These aren't just prompts.
Claude Code has tool use, so a markdown file can run shell
commands, write scripts, read files, make API calls. The prompt
orchestrates everything. A script that runs your tests and reports
results (`run_tests.md`): #!/usr/bin/env claude-
run --permission-mode bypassPermissions Run
./test/run_tests.sh and summarize what passed and failed.
Because stdin/stdout work like any Unix program, you can chain
them: cat data.json | ./analyze.md > results.txt
git log -10 | ./summarize.md ./generate.md |
./review.md > final.txt Or mix them with traditional shell
scripts: for f in logs/\*.txt; do
cat "$f" | ./analyze.md >> summary.txt done This
replaced a lot of Python glue code for us. Tasks that needed LLM
orchestration libraries are now markdown files composed with
standard Unix tools. Composable as building blocks, runnable as
cron jobs, etc. One thing we didn't expect is that these are more
auditable (and shareable) than shell scripts. Install scripts like
`curl -fsSL https://bun.com/install | bash` could become:
`curl -fsSL https://bun.com/install.md | claude-run` Where
install.md says something like "Detect my OS and architecture,
download the right binary from GitHub releases, extract to
~/.local/bin, update my shell config." A normal human can actually
read and verify that. The (really cool) executable markdown idea
and auditability examples are from Pete Koomen (@koomen on X). As
Pete says: "Markdown feels increasingly important in a way I'm not
sure most people have wrapped their heads around yet." We
implemented it and added Unix pipe semantics. Currently works with
Claude Code - hoping to support other AI coding tools too. You can
also route scripts through different cloud providers (AWS Bedrock,
etc.) if you want separate billing for automated jobs. GitHub:
https://github.com/andisearch/claude-switcher What workflows would
you use this for?
Author : jedwhite
Score : 108 points
Date : 2026-01-09 02:29 UTC (20 hours ago)
| serious_angel wrote:
| Oh dear... but... but why let some LLM set of unknown source of
| unknown iteration... execute code... in your machine...?
|
| I was excited in the possibly extravagant implementation idea
| and... when I read enough to realize it's based on some yet
| another LLM... Sorry, no, never. You do you.
| m-hodges wrote:
| > but why let some LLM set of unknown source of unknown
| iteration... execute code... in your machine...?
|
| That's entirely what Claude Code does.
| serious_angel wrote:
| Roger that. Thank you! Apparently, while I've being employed
| in security as software engineer for at least 19 years now,
| I've never ever considered it all serious, and still do not.
|
| Sorry, I have literally no interest in all of it that makes
| you dependent on it, atrophies mind, degrades research and
| social skills, and negates self-confidencen with respect to
| other authors, their work, and attributions. Nor any of my
| colleagues in military and those I know better in person.
|
| Constant research, general IDEs like JetBrains's, IDA Pro,
| Sublime Text, VS Code, etc. backed by forums, chats, and
| Communities, is absolutely enough for the accountable and fun
| work in our teams, who manage to keep in adequate deadlines.
|
| I just disable it everywhere possible, and will do all my
| life. The close case to my environment was VS Code, and
| hopefully there's no reason to build it from source since
| they still leave built-in options to disable it:
| https://stackoverflow.com/a/79534407/5113030 (How can I
| disable GitHub Copilot in VS Code?...)
|
| Isn't it just inadequate to not think and develop your mind,
| and let alone pass control of your environment to a yet
| another model or "advanced T9" of unknown source of unknown
| iteration.
|
| In pentesting, random black-box IO, medicine experimental
| unverified intel, log data approximation why not? But in
| environment control, education, art or programming, fine
| art... No, never ^^
|
| Related: https://www.tomshardware.com/tech-
| industry/artificial-intell...
| jedwhite wrote:
| You can use this without letting the markdown scripts you write
| execute any code at all, whether that is via Claude Code or
| other AI tool in future.
|
| The default permissions are to not allow execution. Which means
| that you can use the eval and text-generation capabilities of
| LLMs to perform assessments and evaluations of piped-in content
| without ever executing code themselves.
|
| The script shebang has to explicitly add the permissions to run
| code, which you control. It supports the full Claude Code flag
| model for this.
| chrismorgan wrote:
| I get the intent, but it's bizarre to hear invocation of
| nondeterministic tools that occasionally delete people's entire
| drives "more auditable".
| jedwhite wrote:
| My view is that readability and ease of understanding have a
| real impact on auditability. Nondeterministic output also
| clearly has a significant impact on auditability.
|
| The balance between readability and determinism for
| auditability partly relates to developer philosophy. Tech is
| famous for religious arguments. I have friends who hate AI
| coding, and want to avoid nondeterminstic tools at all costs.
| And other friends whose productivity has increased
| significantly, and who see the future of programming as natural
| language.
|
| The quality of AI models and tools like Claude Code is
| improving fast, and there are many developers who find value in
| them, myself included. I built this to make life easier for
| developers who want to use AI tools for automation.
|
| I find it much faster to parse and understand plain language
| than many code scripts I've seen. It was one of Python's great
| insights that people spend more time reading code than writing
| it. And there is a tradeoff in auditability between determinism
| and the ability to quickly read and understand what systems do.
|
| There are clearly many people who find AI useful, and who are
| becoming skilled in its use as a tool. This is just a little
| tool that I put together for myself and other people who fall
| in that basket.
|
| Learning where to use AI tools appropriately - how to constrain
| the dangers while maximizing the value - is part of the
| challenge. From using this particular tool for real work, it
| fits some use cases well, and can make things easier both to
| understand and share, as well as to write.
|
| I hope it's useful for some other people wanting to use AI for
| scripting and automation.
|
| I think that quickly understandable instructions are part of
| auditability. Not the whole thing, and their use needs to be
| balanced with safety and security. But an important part of it.
|
| I accept there are plenty of folks who don't see AI tools that
| way. We're sharing this for people who see the value in this
| new approach, even though it is a fast-moving field and there
| are a lot of imperfections.
|
| Any reasonably competent Claude Code user who is careful about
| setting permissions boundaries is no more going to delete their
| hard drive than a competent command line user would. There will
| be things that go wrong with AI, as before it.
|
| In years of tech support, I've personally had to help people
| who neutered their Windows install or deleted files they
| needed. Those things happen and I'd argue they come down to
| skill issues, with AI or without. New tools have a learning
| curve.
|
| I get that you think that's bizarre to see readability with AI-
| based tools as more auditable, and I really do understand that
| perspective.
| signalnine wrote:
| lmao nondeterministic shell scripting
| jedwhite wrote:
| This is absolutely a new type of nondeterministic tool, so
| you're spot on there.
|
| One of the key things we realized starting to use it is that
| the approach allows you to mix deterministic and non-
| deteministic tools together as part of a composable chain.
|
| So you can, for example, use LLMs for their evaluation
| capabilities with a natiural language script as part of a
| broader chain that wraps it in deterministic code, and that
| also can include and run deterministic code nested within the
| plain language script.
|
| So it allows us to create pipelines that combine the best of
| both approaches as appropriate based on the sub-task at hand.
| shakna wrote:
| If you mix deterministic and nondeterministic, then the
| result is nondeterministic.
|
| Which means your entire pipeline is tainted.
|
| If your process is fine with that, whatever, but don't
| pretend that the result can be controlled.
| jedwhite wrote:
| One thing to consider is that the steps in the pipeline can
| be deterministic (the code executed) while the outputs
| (summaries, reviews, evaluations, explanations) may be
| nondeterministic. An example would be summarizing data
| calculated via a traditional script, and piping it to a
| report-format markdown script that generates the report and
| summarizes the results.
|
| I agree that this is a choice by each person using tools
| like this, and that it is up to each of us as developers
| whether a tool like this suits the use case at hand.
|
| My own view is that the world is rapidly moving to more
| human language programming tools, and that system
| automation and shell scripting will be part of this. There
| is a wide array of sensible potential use cases I can see
| between the two polarized views of "never use an LLM' and
| "let's vibe code system automation".
| shakna wrote:
| If the code executed is deterministic - then so is the
| output.
|
| If your output is in any way nondeterministic, then so is
| the code executed. Fin. No nuance to mathematically be
| had.
|
| Randomness is nothing new. Various algorithms have always
| been non-deterministic. Randomness is in most standard
| libraries.
|
| My problem here is not with what you're doing - but that
| you're presenting as if you do not understand what you're
| doing.
| rvz wrote:
| Exactly. The above is a terrible idea.
|
| I guess these so called "developers" these days did not ever
| think about why this is needed. Ever.
|
| The "senior/staff" engineers of 2025 are now at the same
| knowledge level of juniors in 2015 or were not at all "senior"
| to begin with ideas like this.
| imcritic wrote:
| What does any of this have to do with Markdown?
| jedwhite wrote:
| The markdown format provides a way to clearly format and
| structure instructions that Claude Code does well
| understanding, with clear markers for structure/headings,
| tables and code blocks.
|
| Making a markdown `.md` text file executable with Claude Code
| is effective in practice because Claude Code can easily
| understand the content.
| tedk-42 wrote:
| And we're officially going down the drain with linux / command
| line:
|
| ``` #!/usr/bin/env claude-run --permission-mode bypassPermissions
| ```
| jedwhite wrote:
| Claude Code supports a set of flags to control behaviour such
| as permissions, and both `--permission-mode bypassPermissions`
| and `--dangerously-skip-permissions` are examples of those.
|
| The claude-run helper supports passing in those flags supported
| by Claude Code itself that are relevant to a shell-scripting
| like context.
|
| It also adds a couple of convenience flags (`--aws`, `--azure`,
| `--vercel`, `--vertex` for cloud API key use).
| wiether wrote:
| I think I get the idea... but why not officially create a new
| file type altogether?
|
| Not only it would avoid any confusion (Markdown wasn't meant to
| be executable?) but it would allow future extensions in a domain
| that is moving fast.
|
| The recent incident
| (https://news.ycombinator.com/item?id=46532075) regarding Claude
| Code's changelog shows that pure Markdown can break things if it
| is consumed raw.
|
| Also, regarding: "Detect my OS and architecture, download the
| right binary from GitHub releases, extract to ~/.local/bin,
| update my shell config."
|
| I have a hard time seeing how this is "more auditable" than a
| shell script with hardcoded URLs/paths.
|
| "the right binary" is something that would make me reject an
| issue from a PM, asking for clarifications because it's way too
| vague.
|
| But maybe that's why I'll soon get the sack?
| jedwhite wrote:
| Another format is an interesting idea. This tool will work with
| any text file content and file extension. So you could create
| another text-based format yourself and use it in theory.
|
| I think the reasons Markdown is appealing include:
|
| - It's just a text file.
|
| - LLMs like Claude have high comprehension of the format, so
| Claude Code does very well with it.
|
| - You can mix structured and unstructured text, and code with
| plain language: YAML frontmatter, outline/headings, code
| blocks, tables, links and images etc.
|
| I used a heavily condensed version of the example prompt that
| Pete Koomen posted about as a simplified example, so that's
| really just me cutting it back to the most simple form of the
| concept.
|
| In real-use it would be detailed, verbose and specific, and
| include the actual code blocks and external shell script
| references to retrieve and execute. So this really is just a
| proof of concept to give an idea of the sort of thing that
| people could create in future.
|
| I know lots of us developers joke about getting the sack and
| losing out to AI. But for what it's worth, the sorts of points
| you raise are exactly why I think skilled developers become
| even more valuable than ever with AI.
|
| Programming will change massively this next decade. But it has
| many times even in my life. So I'm definitely in the camp that
| thinks this is a new programming abstraction level, and Claude
| Code and Codex and others are useful tools that improve the
| productivity of skilled coders. Especially when they are used
| carefully and thoughtfully.
| JohnKemeny wrote:
| I use .ag and it's YAML-inspired. I have incorporated ideas
| from Design by contract:
| https://news.ycombinator.com/item?id=46554477
| jedwhite wrote:
| The YAML-inspired format is clear, and pretty cool actually.
| You can use those `.ag` files directly with claude-run in the
| shebang or from the command line unmodified. The shebang gets
| stripped before the file is passed to Claude Code.
| rognjen wrote:
| Jupyter notebooks also exist. Also see
| https://en.wikipedia.org/wiki/Literate_programming
| jedwhite wrote:
| I'm also a fan and heavy user of Jupyter notebooks and literate
| programming in general. I think the use case for runnable
| mardown files with AI tooling for automation applies to
| complementary cases.
|
| Having said that, there are ad hoc automation tasks that I've
| traditionally used Jupyter notebooks to do that I'm finding are
| easier to get running using markdown files and Claude Code.
| It's early days and I still am getting a feel for this myself.
|
| There are some comments from earlier with discussion of other
| literal program tools.
| lguzzon wrote:
| Why not MdFlow? https://github.com/johnlindquist/mdflow
| jedwhite wrote:
| Thanks, I hadn't seen that. This tool:
|
| - Lets you make regular Markdown files directly executable
| using shebang line.
|
| - It keeps the Markdown itself clean and standard rather than
| using variable placeholders or any kind of special syntax.
|
| - Includes support for session isolation
|
| - Allows you to keep script use separate from your regular
| Claude Code subscription, by allowing you to specify the
| provider cloud / model in scripts, or switch them on the fly.
|
| Another commenter suggested a custom format for executable llm
| scripts, which looks like the direction mdflow takes.
|
| Using claude-switcher you can also use multiple clouds/keys for
| billing and failover, and to keep your subscription tokens for
| interactive or personal use, which I think is also useful.
| PunchyHamster wrote:
| _Internal screaming intensifies_
| rvz wrote:
| 1)What...
|
| ...could possibly go wrong?
| ceving wrote:
| Did something similar some time ago:
| https://gitlab.com/ceving/mdexec
| oulipo2 wrote:
| There's something similar in concept here: https://runme.dev/
| chrisweekly wrote:
| error: cannot decode raw data
|
| (iOS Safari)
| bsima wrote:
| Ive been doing this for a couple weeks
| Someone wrote:
| There's nothing specific markdown to this. It could just as well
| be some other markup language, plaintext, or even any other
| textual language.
|
| You could, for example, put a C program on lines 2 and further
| and expect/hope/pray Claude to interpret or compile and run that
| (adding a comment _"run the following program; download and
| compile an interpreter or compiler if needed first"_ as an
| instruction to Claude would improve your chances)
| jedwhite wrote:
| Yes, you can use this with any text file and file extension to
| send file content to Claude Code with unix-like pipe support.
| Markdown happens to be a format that models like Claude work
| well with. And they provide a very readable way to mix
| structured and unstructured content along with code. But I use
| this with other plain text files regularly.
|
| You could also pass commented code/scripts straight into Claude
| Code using it quickly without changing how they execute. The
| prompt instructions could go at the top of a valid file (say
| python/typescript) as comments, e.g.
|
| `claude-run --azure --opus my_script.py`
| jimmySixDOF wrote:
| I like it but my only problem with markdown apps like
| Obsidian or GitHub et al is you cant handle prompt templates
| with byo <xml tags> unless you ``` code box ``` them or the
| rendering thinks you have bad html and mess up the remaining
| markdown display. Properly separating text section for LLMs
| makes a big difference in prompt performance and </xml tags>
| are more expressive at doing this than ### markdown headers.
| Other than that I have almost completely shifted to calling
| markdown files into context.
| jedwhite wrote:
| One cool thing is that the claude-run scripts make any text
| file executable with AI, including xml, ymal, etc. So you
| can do something like: #!/usr/bin/env
| claude-run <instructions>
| Analyze this codebase. </instructions>
|
| Then: chmod +x task.xml && ./task.xml
| exe34 wrote:
| https://bellard.org/tcc/tcc-doc.html#:~:text=ab.o.-,Scriptin...
| yakkomajuri wrote:
| A few people have already mentioned similar tools here but one
| worth mentioning is Atuin Desktop (yes, the same shell history
| Atuin): https://blog.atuin.sh/atuin-desktop-runbooks-that-run/
|
| "Executable runbooks" is the name given to the concept there
| jedwhite wrote:
| Thanks, it's great to see people trying different approaches to
| runnable prompts and variations on literate programming. I
| think it's an area with a lot of potential, and I expect there
| will be a lot of interesting ideas come out of it.
| PurpleRamen wrote:
| Looks more like executable prompt-files, as there seem to be no
| extra markdown-handling except removing the shebang. I know AIs
| are good at handling Markdown-Syntax, but do they support other
| markup-languages too? So you could use whatever you want here.
| jedwhite wrote:
| Yes you can use this with any text file format and file
| extension. Markdown just happens to work well with Claude Code
| and is very readable. But some other comments here mention
| `.ag` as a nice alternative, and plain text with C code. But
| you can also use it to send yaml, xml, simple text, or
| commented code in directly.
|
| The scripts are all pretty simple but they also:
|
| - Handle script-context-relevant flags and control code
| execution permissions
|
| - Convenience flags for directing scripts to run across cloud
| providers rather than a personal Claude subscription.
|
| - Session isolation, especially between your regular
| interactive `claude` command and running with API keys
|
| This means that your runnable script use can be kept isolated
| from your regular personal Claude environment that you use for
| interactive development.
| trollbridge wrote:
| Executable markdown? Why not just write a shell script?
| jedwhite wrote:
| There are some tasks that LLMs are good at, but which can be
| hard to do with traditional command line tools or scripts. This
| is true even when you are a skilled coder and expert in Shell
| scripting. Examples include summarization, judgement-based
| evaluation, formatting etc.
|
| Executable markdown provides a method of building these tasks
| into traditional pipelines as small, single-task-focused,
| composable modules. They also have the advantage that they can
| be easily shared and re-used.
| JohnKemeny wrote:
| I have developed my personal agentic file format `.ag` for this
| purpose.
|
| Here is the template I start with:
| #!/usr/bin/env gpt-agent input: <target/context
| (e.g., cwd)> task: | <one clear
| objective> output: | <deliverables +
| required format> require: - <must be
| true before start; otherwise stop + report>
| invariant: - <must stay true while working (scope +
| safety)> ensure: - <must be true at
| the end (definition of done)> rescue: |
| <what to do if any requirement/invariant/ensure cannot be met>
| nullpoint420 wrote:
| Great idea, this reminds me of a Makefile! However, I do dread
| the cmake version of this that will nevertheless emerge in the
| next 10 years.
| jedwhite wrote:
| Thanks for this. I find templates helpful too, and that's a
| neat structure. I use templates heavily with Obsidian for non-
| code tasks also. If you want to try it out, you can use this
| with the claude-run tooling with flags etc with files using
| your `.ag` extension with the modified shebang.
|
| `#!/usr/bin/env claude-run --permission-mode bypassPermissions`
|
| Or use the .ag files you have unmodified:
|
| `claude-run --opus --vercel task.ag`
| zahlman wrote:
| Aside from what several others said about having done something
| similar locally, wouldn't this be a trivial modification to Simon
| Willison's `llm` wrapper?
| jedwhite wrote:
| Big fan of Simon Willison. It would be great to see support for
| executing markdown files directly added to other tools like
| `llm`. And to Claude Code, Codex themselves.
|
| claude-run is just a bunch of little convenience scripts, but
| for it to work effectively with code execution, the handling
| needs to do a little more than just `cat` the file output, for
| example stripping shebang lines, supporting flags and
| permissions and a few other things. But all very simple if you
| see the repo.
|
| Adding support for session isolation and support for different
| cloud providers and API keys to keep things separate from one's
| personal Claude subscription took a little work. But that is
| optional.
| rewilder12 wrote:
| IDK man it feels like you are making a less-useful unsafe wheel.
|
| - file types exist for a reason
|
| - this is just prompt engineering which is already easy to do
| jedwhite wrote:
| I agree that script execution safety is a real concern, as it
| is with AI coding tools generally. By default the runnable
| markdown files do not have permission to execute code, unless
| you specifically add those permissions.
|
| I can see there might be valid arguments for enforcing file
| type associations for execution at the OS level. These are just
| text files, and Unix-like environments support making text
| files executable with a shebang as a universal convention.
|
| I am a fan of that unix-like philosophy generally: tools that
| try to do a single thing well, can be chained together, and
| allow users to flexibly create automations using plain text. So
| I tried to stick with that approach for these scripts.
|
| I'm a bear of little brain, and prompt engineering makes my
| head hurt. So part of the motivation was to be able to save
| prompts and collections of prompts once I've got them working,
| and then execute on demand. I think the high readability of
| markdown as scripts is helpful for creating assets that can be
| saved, shared and re-used, as they are self-documenting.
| yencabulator wrote:
| As far as I understand, by default your claude-shebang files
| inherit the permissions that have been previously granted in
| the current directory you're executing them in.
| jedwhite wrote:
| The ability to execute code is not granted as part of the
| directory permissions. By default the scripts will not be
| able to execute code, only run analysis and text gen tasks.
| You need to explicitly add the flags for permissions to
| execute code. There is an example of this above and a few
| more in the repo README.
| yencabulator wrote:
| Why wouldn't Claude Code, called by you, do its normal
| .claude/settings.local.json processing?
| jedwhite wrote:
| The constraints work consistent with Claude's -p mode. It
| is isolated from your regular Claude interactive sessions
| and settings on purpose. And that makes it safer by
| default because you have to explicitly add permissions.
|
| You can try this out and you'll see what I mean if you
| run a few simple examples. This approach was based on
| experimentation and trying to be consistent with Claude's
| own philosophy here.
| yencabulator wrote:
| Ah so -p doesn't follow the local settings. TIL.
| DocTomoe wrote:
| So ... you are letting a nondeterministic LLM operate on the
| shell, via quasi-shellscript. This will appeal mostly to people
| who do not have the skillset to write an actual shell-script.
|
| In short, isn't that like giving a voice-controlled scalpel to a
| random guy on the street an tell them 'just tell it to
| neurosurgery', and hope it accidentally does the right procedure?
| jrmg wrote:
| Don't worry, it's "more auditable"!
| jedwhite wrote:
| I know this will not appeal to developers who don't see a
| legitimate role for the use of AI coding tools with
| nondeterministic output.
|
| It is intended to be a useful complement to traditional Shell
| scripting, Python scripting etc. for people who want to add
| composable AI tooling to their automation pipelines.
|
| I also find that it helps improve the reliability of AI in
| workflows when you can break down prompts into re-useable
| single-task-focused modules that leverage LLMs for tasks they
| are good at (format.md, summarize-logs.md, etc). These can then
| be chained with traditional Shell scripts and command line
| tools.
|
| Examples are summarizing reports, formatting content. These
| become composable building blocks.
|
| So I hope that is something that has practical utility even for
| users like yourself who don't see a role for plain language
| prompting in automation per se.
|
| In practice this is a way to add composable AI-based tooling
| into scripts.
|
| Many people are concerned about (or outright opposed to) the
| use of AI coding tools. I get that this will not be useful for
| them. Many folks like myself find tools like Claude helpful,
| and this just makes it easier to use them in automation
| pipelines.
| DocTomoe wrote:
| I'm more concerned that someone decides to prompt for
| 'analyze these logfiles, then clean up', and the LLM randomly
| decides the best way to 'clean up' is a 'rm -rf /' - not on
| the first run, but on the 27th.
|
| That kind of failure mode is fundamentally different from
| traditional scripting: it passes tests, builds trust, and
| then fails catastrophically once the implicit interpretation
| shifts.
|
| In short: I believe it's nice this works for the engineer who
| knows exactly what (s)he is doing - but those folks usually
| don't need LLMs, they just write the code. People who this
| appeals to - and who may not begin to think about side-
| effects of innocent-sounding prompts - are being given a foot
| machine gun, which may act like a genie with hilarious
| unintended consequences.
| anthk wrote:
| A shitty org-mode reinvention, now without being reproducible.
| calvinmorrison wrote:
| One silly fun thing about PHP is php tags. So you can do
| notebooks like this for kinda free... if you want to execute
| code? just put it in <?php ?> blocks.
| linkregister wrote:
| I found this useful.
|
| This could be dinosaur mindset from 2022, but would it not make
| sense to prompt the LLM to create a bash script based on these
| instructions, so it could be more deterministic? Claude code is
| pretty reliable, but this is probably only one and a half nines
| at best.
|
| As for safety, running this in a devcontainer[1][2] or as part of
| a CI system should be completely fine.
|
| 1. (conventional usage)
| https://code.visualstudio.com/docs/devcontainers/containers
|
| 2. (actual spec) https://containers.dev/
| jedwhite wrote:
| Thank you, and yes! That is what I already frequently do for
| quick automation tasks.
|
| As you say, Claude is actually very good at writing shell
| scripts and using tools on-the-fly. But I know there is an AI-
| confidence factor involved for developers making the choice to
| leverage that.
|
| For simple tasks (in practice) I already find you can often
| prompt the whole thing.
|
| For tasks where you already have the other traditional scripts
| or building blocks, or where it is complex, then you might
| break it up.
|
| Interestingly, you can intermix these approaches.
|
| You can have runnable markdown that writes and runs scripts on
| the fly, mixed with running command line tools, and chained
| along with traditional tools in a bash script, and then call
| that script from a runnable markdown that passes in test
| results, or analyzes the code base and passes recommendations
| in.
|
| The composability and ability to combine and embed code blocks
| and tool use within plain language is quite powerful. I'm still
| learning how to use this.
|
| I'm glad it is already useful and thank you.
| jedwhite wrote:
| Also +1 to using containers and sandboxed environments! It
| means you can yolo it and skip permissions dangerously to
| experiment with vibe automation :)
|
| More seriously, I agree that setting permissions to the
| minimum needed for the task and using sandboxed containers is
| sensible.
| VikingCoder wrote:
| Does it help get repeatable results if you say, "Use a random
| seed of 42 for this task"? Or if you somehow lower the
| temperature, so it's more deterministic?
| jedwhite wrote:
| At the moment, it looks like Claude Code does not support using
| 'temperature' or 'seed' flags. It would be awesome if they add
| that.
|
| Using the request to use a seed within the prompt will mean
| that when Claude rights the code it could use that seed inside
| what it writes for randomize functions. But sadly it wouldn't
| impact Claude's own text generation's determinism.
|
| There is active interest on GitHub to support this. But the
| most recent issue with it I could see was closed in July as
| "not planned"
| VikingCoder wrote:
| cat StarWars.mkv > claude "Make Leia the hero Jedi warrior, and
| Luke the handsome prince she rescues" > vlc
| ksherlock wrote:
| I'm not the target demographic, but this seems like a step
| backwards.
|
| Like, once upon a time maybe you gave your jr programmer a list
| of things to do, and depending on their skill, familiarity with
| the cli, hangover status, spelling abilities, etc, you'll get
| different results. So you write a deterministic shell script.
| jedwhite wrote:
| I know there are two polarized camps on the topic of AI coding.
| Even for people who are concerned about it and prefer to use
| traditional scripting, there are some benefits worth
| considering in having runnable, composable prompt modules.
|
| There are some tasks that are challenging to achieve with
| traditional code, but where modern LLMs perform strongly.
|
| Examples include summarization, complex content formatting and
| restructuring, natural language classification, and evaluation
| judgements.
|
| I've found that it is useful to be able to easily incorporate
| these along with traditional Shell scripts and command line
| tools as part of workflow pipelines. And I hope it can be
| useful for other people too.
___________________________________________________________________
(page generated 2026-01-09 23:01 UTC)