adr-kit
AGENTS.md13 starsChanged 4 months agoMITView on GitHub
These instructions adapt the repository guidance for Codex and other coding agents working in adr-kit. - Treat Backlog.md as the source of truth for meaningful work. - Search for an existing task before starting implementation work. - If no task exists, create one before editing code or docs. - Prefer the Backlog MCP tools for reading, searching, creating, and updating tasks. Use the backlog CLI only when MCP is unavailable or insufficient. - Do not edit files in backlog/tasks/ directly.…
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 repository19 other files it gives its agents.
The file
We split this AGENTS.md into the rules it gives an agent
11 rules. About 0 are common, 7 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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
- Distinctive: line 8
Treat Backlog.md as the source of truth for meaningful work.
- Distinctive: line 9
Search for an existing task before starting implementation work.
- Distinctive: line 10
If no task exists, create one before editing code or docs.
- Very specific: line 11
Prefer the Backlog MCP tools for reading, searching, creating, and updating tasks.
- Very specific: line 13
Do not edit files in backlog/tasks/ directly.
- Distinctive: line 14
Keep tasks small enough to finish in one focused pass.
- Distinctive: line 18
Keep changes small, focused, and dependency-free unless the roadmap says otherwise.
- Very specific: line 20
Follow the existing adr-kit conventions in README.md, ROADMAP.md, and CLAUDE.md.
- Distinctive: line 26
Run the smallest test or check that proves the change.
- Distinctive: line 29
Before marking work done, make sure the task status and notes in Backlog are updated to match the actual change.
- Very specific: line 35
Read .adr-kit/ADR-guide.md before architectural changes.
≈ “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
adr-kit Agent Instructions
These instructions adapt the repository guidance for Codex and other coding
agents working in adr-kit.
Task management
- Treat Backlog.md as the source of truth for meaningful work.
- Search for an existing task before starting implementation work.
- If no task exists, create one before editing code or docs.
- Prefer the Backlog MCP tools for reading, searching, creating, and updating
tasks. Use the
backlogCLI only when MCP is unavailable or insufficient. - Do not edit files in
backlog/tasks/directly. - Keep tasks small enough to finish in one focused pass.
Repo conventions
- Keep changes small, focused, and dependency-free unless the roadmap says otherwise.
- Follow the existing adr-kit conventions in
README.md,ROADMAP.md, andCLAUDE.md. - Favor deterministic, stdlib-first changes over new runtime dependencies.
Verification
- Run the smallest test or check that proves the change.
- Broaden verification when the change touches shared behavior, tooling, package layout, or user-facing workflow.
- Before marking work done, make sure the task status and notes in Backlog are updated to match the actual change.
<!-- ADR-KIT CODEX START -->ADR Kit
Read .adr-kit/ADR-guide.md before architectural changes. Architecture decisions live in docs/adr/. Use $adr-kit:context before implementation, $adr-kit:adr for new decisions, and $adr-kit:judge before commit.
<!-- ADR-KIT CODEX 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.

