noodle
AGENTS.md259 starsChanged 35 days agoApache-2.0View on GitHub
NOTE: Everything in docs/ is for people using Noodle. Code is documented only in its own comments; see the no-code-docs skill. Write for someone who has never seen the code or the author's machine, conversation or work history. - Document what people can do, how to do it, and the limits they will meet, in plain language. - Do not describe how the code works: no architecture, design reasoning, implementation notes, formats, protocols, sandbox rules, internal limits or build and…
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 31,439 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 repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- Applet/AGENTS.mdAGENTS.md
- Browser/AGENTS.mdAGENTS.md
- Computer/AGENTS.mdAGENTS.md
- Hub/AGENTS.mdAGENTS.md
- Incubator/AGENTS.mdAGENTS.md
- Mobile/AGENTS.mdAGENTS.md
- Terminal/AGENTS.mdAGENTS.md
- Tools/AGENTS.mdAGENTS.md
- agents-md-symlinkSkill
- apple-history-utilitiesSkill
- helper-visibilitySkill
- mint-releaseSkill
- no-code-docsSkill
- sheet-and-settings-sizingSkill
- test-first-changesSkill
- ui-copySkill
- version-bound-cleanupSkill
The file
We split this AGENTS.md into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Document what people can do, how to do it, and the limits they will meet, in plain language.
- Distinctive: line 9
Do not describe how the code works: no architecture, design reasoning, implementation notes, formats, protocols, sandbox rules, internal …
- Distinctive: line 12
Do not name or link source files, types or functions.
- Distinctive: line 13
Do not add internal notes, audits, work logs, session summaries, investigation diaries, dated verification reports, cleanup inventories, or …
- Distinctive: line 15
Keep temporary findings in the task conversation and release history in the appropriate changelog.
- Distinctive: line 17
Update an existing guide before adding a file.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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
Documentation
NOTE: Everything in docs/ is for people using Noodle. Code is documented
only in its own comments; see the no-code-docs skill. Write for someone who
has never seen the code or the author's machine, conversation or work history.
- Document what people can do, how to do it, and the limits they will meet, in plain language.
- Do not describe how the code works: no architecture, design reasoning, implementation notes, formats, protocols, sandbox rules, internal limits or build and test commands. Put what the code needs explained in comments beside it.
- Do not name or link source files, types or functions.
- Do not add internal notes, audits, work logs, session summaries, investigation diaries, dated verification reports, cleanup inventories, or task checklists. Keep temporary findings in the task conversation and release history in the appropriate changelog.
- Update an existing guide before adding a file. Remove obsolete material and repair links when consolidating or deleting documentation.
- Message, event and command guidance lives only in the messenger documentation
in the source. Do not copy it into a guide; point to
messenger --help.
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.