agentic-toolbox / maintainers
AGENTS.md5 starsChanged 46 days agoMITView on GitHub
Entry point for sessions that work on this repository itself: skills, docs, packages, or process. Agents that only use the toolbox stop at the root AGENTS.md and do not load this file. Read the root AGENTS.md and docs/SDLC.md first. This file adds only what is specific to building this repository. Write agent text to the writing standard. The tracker skill path in ## Tracker is relative to this directory: maintainers/.agents/tracker/SKILL.md. Linear — load .agents/tracker/SKILL.md (tracker-sdlc v2). Parallelism: max Agent text:…
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 31,774 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 repository49 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- buying-researcherSkill
- cursor-cloud-agents-whenSkill
- debug-anthropicSkill
- debug-pocockSkill
- debugSkill
- discover-the-ideaSkill
- docs-google-styleSkill
- golang-safetySkill
- golang-securitySkill
- golang-testingSkill
- grok-acpSkill
- host-config-pyinfraSkill
- lang-cppSkill
- lang-csharpSkill
- lang-cSkill
- lang-dartSkill
- lang-dockerSkill
- lang-goSkill
- lang-javaSkill
- lang-js-tsSkill
- lang-kotlinSkill
- lang-luaSkill
- lang-makefileSkill
- lang-phpSkill
- lang-powershellSkill
- lang-protobufSkill
- lang-pythonSkill
- lang-rubySkill
- lang-rustSkill
- lang-shellSkill
- lang-sqlSkill
- lang-swiftSkill
- lang-terraformSkill
- language-routerSkill
- lang-web-markupSkill
- modern-pythonSkill
- pr-reviewSkill
- sdlc-artifactsSkill
- sdlc-onboardingSkill
- security-hardeningSkill
- shell-safetySkill
- tddSkill
- tracker-sdlcSkill
- ui-craftSkill
- ux-designSkill
- verify-before-doneSkill
- yagniSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Read the root AGENTS.md and docs/SDLC.md first.
- Distinctive: line 9
Write agent text to the writing standard.
- Very specific: line 31
Write one run file per model in evals/runs/.
- Very specific: line 35
After the merge, that run becomes the model's row in baseline.md.
≈ “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
AGENTS (maintainers)
Entry point for sessions that work on this repository itself: skills, docs, packages, or process. Agents that only use the toolbox stop at the root AGENTS.md and do not load this file.
Read the root AGENTS.md and docs/SDLC.md first. This file adds only what is specific to building this repository. Write agent text to the writing standard.
The tracker skill path in ## Tracker is relative to this directory:
maintainers/.agents/tracker/SKILL.md.
Tracker
Linear — load .agents/tracker/SKILL.md (tracker-sdlc v2).
Execution
Parallelism: max
Evals
Agent text: AGENTS.md, docs/SDLC.md, docs/sdlc/, docs/INTAKE.md,
skills/.
- A PR into
mainthat changes agent text gets an eval run before it merges: T1–T3 on the PR's head, three repeats per task, on each model in evals/baseline.md, per evals/procedure.md. - Write one run file per model in
evals/runs/. The PR description lists regressions against the baseline first. - The operator, or someone the operator names in writing, decides from the report: merge, fix, or rerun. Tokens and wall time never decide.
- After the merge, that run becomes the model's row in
baseline.md. - A new daily-driver model → run T1–T3 on
mainand add its row before the next PR intomainthat changes agent text.
Where notes go
- Design records:
maintainers/design/<chunk>/(HLD, LLD, UX, comparables), shapes fromsdlc-artifacts. - Planning notes (candidates, plans, goals):
maintainers/. - Everything here is agent context under the root Public repo rule: informal is fine, but civil and credential-free. No tone review.
- Skills, human-facing docs, and packages stay where the root
AGENTS.mdputs them; they never link intomaintainers/for routing.
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.