beads-utils
AGENTS.md2 starsChanged 6 days agoMITView on GitHub
Project context, the script catalog, coding conventions, and how to run and test everything live in CLAUDE.md — read it first; it is the canonical doc for this repo. This file holds only generic agent-execution guidance. Per-script design notes live in .claude/rules/, one plain Markdown file per area; Claude Code loads them by path, and any other agent should read the matching one before changing a script. (The beads issue-tracker section below is auto-generated by bd; don't hand-edit it.) Shell…
- Commits and pushes
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 repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- changelogSkill
- close-shopSkill
- deferSkill
- finalizeSkill
- review-titlesSkill
- start-taskSkill
- statusSkill
The file
We split this AGENTS.md into the rules it gives an agent
8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 52
Use bd for ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists
- Very specific: line 53
Run bd prime for detailed command reference and session close protocol
- Very specific: line 54
Use bd remember for persistent knowledge — do NOT use MEMORY.md files
- Distinctive: line 62
File issues for remaining work: - Create issues for anything that needs follow-up
- Distinctive: line 73
Verify: - All changes committed AND pushed
- Distinctive: line 78
NEVER stop before pushing - that leaves work stranded locally
- Distinctive: line 79
NEVER say "ready to push when you are" - YOU must push
- Distinctive: line 80
If push fails, resolve and retry until it succeeds <!-- END BEADS INTEGRATION -->
≈ “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
Agent Instructions
Project context, the script catalog, coding conventions, and how to run and
test everything live in CLAUDE.md — read it first; it is the
canonical doc for this repo. This file holds only generic agent-execution
guidance. Per-script design notes live in .claude/rules/,
one plain Markdown file per area; Claude Code loads them by path, and any other
agent should read the matching one before changing a script. (The beads
issue-tracker section below is auto-generated by bd; don't hand-edit it.)
Non-Interactive Shell Commands
Shell commands like cp, mv, and rm may be aliased to cp -i / mv -i /
rm -i (Oh-My-Zsh's common-aliases does this), and an agent shell that
sources the user's profile inherits them. The prompt then waits on stdin
nobody will answer, and the command hangs until the tool times out.
Bypass the alias rather than adding -f:
command cp source dest # or /bin/cp
command mv source dest
command rm file
command cp -R source dest # recursive forms too-f is not a reliable fix. Checked on macOS against the aliases: mv -f and
rm -f do override the -i, but cp -f still prompts, and with no answer
it silently skips the copy, so a script carries on as if it had succeeded.
Other commands that may prompt:
scp- use-o BatchMode=yesfor non-interactivessh- use-o BatchMode=yesto fail instead of promptingapt-get- use-yflagbrew- useHOMEBREW_NO_AUTO_UPDATE=1env var
<!-- BEGIN BEADS INTEGRATION v:1 profile:minimal hash:ca08a54f -->Beads Issue Tracker
This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands.
Quick Reference
bd ready # Find available work
bd show <id> # View issue details
bd update <id> --claim # Claim work
bd close <id> # Complete workRules
- Use
bdfor ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists - Run
bd primefor detailed command reference and session close protocol - Use
bd rememberfor persistent knowledge — do NOT use MEMORY.md files
Session Completion
When ending a work session, you MUST complete ALL steps below. Work is NOT complete until git push succeeds.
MANDATORY WORKFLOW:
- File issues for remaining work - Create issues for anything that needs follow-up
- Run quality gates (if code changed) - Tests, linters, builds
- Update issue status - Close finished work, update in-progress items
- PUSH TO REMOTE - This is MANDATORY:
git pull --rebase bd dolt push git push git status # MUST show "up to date with origin" - Clean up - Clear stashes, prune remote branches
- Verify - All changes committed AND pushed
- Hand off - Provide context for next session
CRITICAL RULES:
- Work is NOT complete until
git pushsucceeds - NEVER stop before pushing - that leaves work stranded locally
- NEVER say "ready to push when you are" - YOU must push
- If push fails, resolve and retry until it succeeds
<!-- END BEADS INTEGRATION -->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.

