my-hermes-skills
AGENTS.md3 starsChanged 10 days agoMITView on GitHub
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 32,671 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 repository20 other files it gives its agents.
- covidence-full-text-reviewSkill
- covidence-full-text-retrievalSkill
- covidence-screeningSkill
- impeccableSkill
- ilearning-autoadvanceSkill
- oh-my-piSkill
- auditing-worktreesSkill
- camofox-browserSkill
- demo-runbookSkill
- hermes-deepseek-cacheSkill
- i-have-adhdSkill
- memory-uiSkill
- multi-repo-pr-review-merge-roundSkill
- oh-my-ghosttySkill
- tldrSkill
- writing-reportsSkill
- sci-hub-accessSkill
- slack-mention-watchSkill
- slack-scanSkill
- superpowers-using-superpowersSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 6
After a review result: if any finding is P0/P1, or overall_correctness is "incorrect", spawn reviewer-deep on the affected files for a …
- Very specific: line 11
NEVER hub wait on a read-only agent (reviewer, reviewer-deep, scout) while other independent work exists.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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.md — oh-my-pi agent rules
Review workflow (two-tier)
- Implementation and review go through task agents. The
revieweragent is the FAST triage pass — do not escalate its model. - After a review result: if any finding is P0/P1, or
overall_correctnessis"incorrect", spawnreviewer-deepon the affected files for a second pass. Otherwise accept the result and move on. reviewer-deepis slow and thorough; only spawn it when the triage pass warrants it, never by default.
Parallelism
- NEVER
hub waiton a read-only agent (reviewer,reviewer-deep,scout) while other independent work exists. Spawn independent tasks in parallel batches; only wait when the next step genuinely depends on the result. - Skip project-wide validation (build/lint/test) inside task agents; run those once at the end in the main session.
- Decide cross-task contracts up front and state them in the batch context; do not let agents negotiate interfaces mid-flight.
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.

