agentleFS
steveyeggesteveyegge/gastown/AGENTS.md

gastown

AGENTS.md19k starsChanged 4 months agoMITView on GitHub

See CLAUDE.md for complete agent context and instructions. This file exists for compatibility with tools that look for AGENTS.md. Recovery: Run gt prime after compaction, clear, or new session Full context is injected by gt prime at session start. This project uses beads for issue tracking. Issues live in .beads/ and are tracked in git. Two CLIs: bd (issue CRUD) and bv (graph-aware triage, read-only). NEVER run bare bv — it launches interactive TUI. Always use --robot-* flags: This workspace…

  • Commits and pushes

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

10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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. Distinctive:

    Never print "Hey @name" — the other agent cannot see your terminal output.

    line 99
  2. Very specific:

    After compaction or new session, run gt prime to reload your full role context, identity, and any pending work.

    line 129
  3. Very specific:

    Use bd for ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists

    line 156
  4. Very specific:

    Run gt prime for detailed command reference and session close protocol

    line 157
  5. Very specific:

    Use bd remember for persistent knowledge — do NOT use MEMORY.md files

    line 158
  6. Distinctive:

    File issues for remaining work: - Create issues for anything that needs follow-up

    line 166
  7. Distinctive:

    Verify: - All changes committed AND pushed

    line 177
  8. Distinctive:

    NEVER stop before pushing - that leaves work stranded locally

    line 182
  9. Distinctive:

    NEVER say "ready to push when you are" - YOU must push

    line 183
  10. Distinctive:

    If push fails, resolve and retry until it succeeds <!-- END BEADS INTEGRATION -->

    line 184

≈ “Common” is an estimate: at least 1 in 5 of the 36,368 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

Agent Instructions

See CLAUDE.md for complete agent context and instructions.

This file exists for compatibility with tools that look for AGENTS.md.

Recovery: Run gt prime after compaction, clear, or new session

Full context is injected by gt prime at session start.

<!-- beads-agent-instructions-v2 -->

Beads Workflow Integration

This project uses beads for issue tracking. Issues live in .beads/ and are tracked in git.

Two CLIs: bd (issue CRUD) and bv (graph-aware triage, read-only).

bd: Issue Management

bd ready              # Unblocked issues ready to work
bd list --status=open # All open issues
bd show <id>          # Full details with dependencies
bd create --title="..." --type=task --priority=2
bd update <id> --status=in_progress
bd close <id>         # Mark complete
bd close <id1> <id2>  # Close multiple
bd dep add <a> <b>    # a depends on b
bd sync               # Sync with git

bv: Graph Analysis (read-only)

NEVER run bare bv — it launches interactive TUI. Always use --robot-* flags:

bv --robot-triage     # Ranked picks, quick wins, blockers, health
bv --robot-next       # Single top pick + claim command
bv --robot-plan       # Parallel execution tracks
bv --robot-alerts     # Stale issues, cascades, mismatches
bv --robot-insights   # Full graph metrics: PageRank, betweenness, cycles

Workflow

  1. Start: bd ready (or bv --robot-triage for graph analysis)
  2. Claim: bd update <id> --status=in_progress
  3. Work: Implement the task
  4. Complete: bd close <id>
  5. Sync: bd sync at session end

Session Close Protocol

git status            # Check what changed
git add <files>       # Stage code changes
bd sync               # Commit beads changes
git commit -m "..."   # Commit code
bd sync               # Commit any new beads changes
git push              # Push to remote

Key Concepts

  • Priority: P0=critical, P1=high, P2=medium, P3=low, P4=backlog (numbers only)
  • Types: task, bug, feature, epic, question, docs
  • Dependencies: bd ready shows only unblocked work
<!-- end-beads-agent-instructions --><!-- gastown-agent-instructions-v1 -->

Gas Town Multi-Agent Communication

This workspace is part of a Gas Town multi-agent environment. You communicate with other agents using gt commands — never by printing text or using raw tmux.

Nudging Agents (Immediate Delivery)

gt nudge sends a message directly to another agent's active session:

gt nudge mayor "Status update: PR review complete"
gt nudge laneassist/crew/dom "Check your mail — PR ready for review"
gt nudge witness "Polecat health check needed"
gt nudge refinery "Merge queue has items"

Target formats:

  • Role shortcuts: mayor, deacon, witness, refinery
  • Full path: <rig>/crew/<name>, <rig>/polecats/<name>

Important: gt nudge is the ONLY way to send text to another agent's session. Never print "Hey @name" — the other agent cannot see your terminal output.

Sending Mail (Persistent Messages)

gt mail sends messages that persist across session restarts:

# Reading
gt mail inbox                    # List messages
gt mail read <id>                # Read a specific message

# Sending (use --stdin for multi-line content)
gt mail send mayor/ -s "Subject" -m "Short message"
gt mail send laneassist/crew/dom -s "PR Review" --stdin <<'BODY'
Multi-line message content here.
Details about the PR and what to look for.
BODY
gt mail send --human -s "Subject" -m "Message to overseer"

When to Use Which

Want to...CommandWhy
Wake a sleeping agentgt nudge <target> "msg"Immediate delivery
Send detailed task/infogt mail send <target> -s "..." --stdinPersists across restarts
Both: send + wakegt mail send then gt nudgeMail carries payload, nudge wakes

Context Recovery

After compaction or new session, run gt prime to reload your full role context, identity, and any pending work.

gt prime              # Full context reload
gt hook               # Check for assigned work
gt mail inbox         # Check for messages
<!-- end-gastown-agent-instructions --><!-- BEGIN BEADS INTEGRATION v:1 profile:minimal hash:ca08a54f -->

Beads Issue Tracker

This project uses bd (beads) for issue tracking. Run gt 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 work

Rules

  • Use bd for ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists
  • Run gt prime for detailed command reference and session close protocol
  • Use bd remember for 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:

  1. File issues for remaining work - Create issues for anything that needs follow-up
  2. Run quality gates (if code changed) - Tests, linters, builds
  3. Update issue status - Close finished work, update in-progress items
  4. PUSH TO REMOTE - This is MANDATORY:
    git pull --rebase
    bd dolt push
    git push
    git status  # MUST show "up to date with origin"
  5. Clean up - Clear stashes, prune remote branches
  6. Verify - All changes committed AND pushed
  7. Hand off - Provide context for next session

CRITICAL RULES:

  • Work is NOT complete until git push succeeds
  • 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 -->

Download now (ZIP)

Trending

Less talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 30 mentionsFeb 2026: 12 mentionsMar 2026: 12 mentionsApr 2026: 3 mentionsMay 2026: 1 mentionJun 2026: 2 mentionsJul 2026: 5 mentionsAug 2026: 6 mentionsSep 2026: 2 mentionsOct 2026: 1 mentionNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the steveyegge/gastown repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about steveyegge/gastown

The biggest 5 of 74 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 74

Talked about on GitHub, YouTube, Bluesky and Hacker News (74 times).

On GitHub · 38

33 more on GitHub

On YouTube · 25

20 more on YouTube

On Bluesky · 7

2 more on Bluesky

On Hacker News · 4

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. gastownhall/gastown★ 18k100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • 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 28,693 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 repository5 other files it gives its agents.

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.