agentleFS
Sign inStart free
whatsnew-fyiwhatsnew-fyi/skills/AGENTS.md

skills

AGENTS.md1 starsChanged 29 days agoMITView on GitHub

You maintain What's New's public agent skills: a Claude Code plugin marketplace whose one plugin, whatsnew, ships Agent Skills that answer dependency questions from the What's New MCP server, plus one publisher skill that writes changelogs in the Declarative Changelogs format (ADR 2026-09.vyb9). People install these into their own agents, so every skill must be useful to someone who has never heard of What's New. - Before editing a SKILL.md or a skill script: READ .agents/rules/skill-authoring.md. - If a change…

  • 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 repository2 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 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.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before editing a SKILL.md or a skill script: READ .agents/rules/skill-authoring.md.

    line 19
  2. Very specific:

    RUN the checks in .agents/context/commands.md.

    line 36
  3. Very specific:

    ADD a decision with python3 scripts/adr.py new "<title>", then index.

    line 37
  4. Very specific:

    WRITE to .agents/memory/, which is read/write by design.

    line 38

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md

Identity

You maintain What's New's public agent skills: a Claude Code plugin marketplace whose one plugin, whatsnew, ships Agent Skills that answer dependency questions from the What's New MCP server, plus one publisher skill that writes changelogs in the Declarative Changelogs format (ADR 2026-09.vyb9). People install these into their own agents, so every skill must be useful to someone who has never heard of What's New.

  • .claude-plugin/marketplace.json: the marketplace (whatsnew-fyi).
  • plugins/whatsnew/: the plugin, with its skills, .mcp.json and evals.
  • tests/: unit tests for the skills' scripts, against real recorded reports.
  • .agents/: context for working on this repo. It is not shipped.

Context routing

  • Before editing a SKILL.md or a skill script: READ .agents/rules/skill-authoring.md.
  • If a change touches what a skill sends to the server or reads back: READ .agents/context/mcp-tools.md.
  • If changing manifests, install names, versions, or cutting a release: READ .agents/context/distribution.md.
  • Before running checks or evals, and before calling a change finished: READ .agents/context/commands.md.
  • Before touching any file: MATCH the task against the trigger table in .agents/rules/decisions.md, and READ every ADR a matching row names.
  • If making an architectural or scope decision: CONSULT .agents/memory/decisions.md, then record the new one per .agents/rules/decisions.md.

Capabilities

  • RUN the checks in .agents/context/commands.md.
  • ADD a decision with python3 scripts/adr.py new "<title>", then index.
  • WRITE to .agents/memory/, which is read/write by design.

Maintenance

This file is a router, not a store. Durable knowledge goes in .agents/: standing rules in rules/, decisions in memory/decisions/, reference in context/. It never goes here, and never into host-local agent memory. Add a routing line only when nothing points at the new file yet.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free