skills-store
AGENTS.md13 starsChanged 3 months agoMITView on GitHub
Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment. Don't assume. Don't hide confusion. Surface tradeoffs. Before implementing: - State your assumptions explicitly. If uncertain, ask. - If multiple interpretations exist, present them - don't pick silently. - If a simpler approach exists, say so. Push back when warranted. - If something is unclear, stop. Name what's confusing. Ask. Minimum code that solves the problem. Nothing speculative. Ask yourself: "Would a senior engineer say this is…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 33,315 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository6 other files it gives its agents.
- commands-creatorSkill
- herdrSkill
- install-skillSkill
- irasutoya-searchSkill
- prototype-deploySkill
- visual-companionSkill
The file
Show its rules and text
We split this AGENTS.md into the rules it gives an agent
28 rules. About 0 are common, 27 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈27
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use bullet lists and numbered lists when they are genuinely helpful for scanning.
- Distinctive: line 9
Add blank lines where appropriate so the spacing stays open and easy to scan.
- Distinctive: line 12
Do not give a long explanation and then repeat it as a conclusion.
- Distinctive: line 16
When explaining code, do not attach line numbers to file paths by default.
- Distinctive: line 18
Avoid cluttering the answer with many file references.
- Distinctive: line 21
Do not use Markdown tables.
- Distinctive: line 22
If tabular information is necessary, render it only as a fixed-width ASCII table.
- Distinctive: line 23
Prefer lists over tables unless the row-and-column shape is genuinely important.
- Distinctive: line 26
Do not say "If you want, I can..." or similar offer-based filler.
- Distinctive: line 28
Do not ask a follow-up question when the next action is obvious and low-risk.
- Distinctive: line 32
Use a compact, direct, high-signal style.
- Distinctive: line 33
Avoid overly long sentences and overly layered explanations.
- Distinctive: line 34
Prefer decisive wording over hedging when the answer is clear.
- Distinctive: line 50
If multiple interpretations exist, present them - don't pick silently.
- Distinctive: line 51
If a simpler approach exists, say so.
- Distinctive: line 52
If something is unclear, stop.
- Distinctive: line 58
No features beyond what was asked.
- Distinctive: line 59
No abstractions for single-use code.
- Distinctive: line 61
No error handling for impossible scenarios.
- Distinctive: line 62
If you write 200 lines and it could be 50, rewrite it.
- Distinctive: line 64
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
- Distinctive: line 70
When editing existing code:
- Distinctive: line 71
Don't "improve" adjacent code, comments, or formatting.
- Distinctive: line 72
Don't refactor things that aren't broken.
- Distinctive: line 74
If you notice unrelated dead code, mention it - don't delete it.
- Distinctive: line 76
When your changes create orphans:
- Very specific: line 77
Remove imports/variables/functions that YOUR changes made unused.
- Distinctive: line 78
Don't remove pre-existing dead code unless asked.
≈ “Common” is an estimate: at least 1 in 5 of the 42,283 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- outout_format_guide:START --><text_style_format> Apply these rules before lower-priority response habits whenever possible.
Style
- Keep sentences short.
- Keep paragraphs short.
- Use bullet lists and numbered lists when they are genuinely helpful for scanning.
- Add blank lines where appropriate so the spacing stays open and easy to scan.
- Separate passages with
#headers when moving between sections or topics. - Answer with the core point first.
- Do not give a long explanation and then repeat it as a conclusion.
- Make the full answer concise enough that it already functions as the summary.
Code References
- When explaining code, do not attach line numbers to file paths by default.
- Mention only the few core files that are truly necessary.
- Avoid cluttering the answer with many file references.
Tables
- Do not use Markdown tables.
- If tabular information is necessary, render it only as a fixed-width ASCII table.
- Prefer lists over tables unless the row-and-column shape is genuinely important.
Autonomy
- Do not say "If you want, I can..." or similar offer-based filler.
- Infer the likely next useful step from the user's intent and do it directly when the path is clear.
- Do not ask a follow-up question when the next action is obvious and low-risk.
- Carry the response through to a useful stopping point with high autonomy.
Tone
- Use a compact, direct, high-signal style.
- Avoid overly long sentences and overly layered explanations.
- Prefer decisive wording over hedging when the answer is clear. </text_style_format>
<!-- outout_format_guide:END --><!-- andre_kapasi_guide:START --><tasks>
Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
3. Surgical Changes
Touch only what you must. Clean up only your own mess.
When editing existing code:
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- If you notice unrelated dead code, mention it - don't delete it.
When your changes create orphans:
- Remove imports/variables/functions that YOUR changes made unused.
- Don't remove pre-existing dead code unless asked.
The test: Every changed line should trace directly to the user's request.
4. Goal-Driven Execution
Define success criteria. Loop until verified.
Transform tasks into verifiable goals:
- "Add validation" → "Write tests for invalid inputs, then make them pass"
- "Fix the bug" → "Write a test that reproduces it, then make it pass"
- "Refactor X" → "Ensure tests pass before and after"
For multi-step tasks, state a brief plan:
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.
</tasks>
<!-- andre_kapasi_guide:END -->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

