AGENTS.md
AGENTS.mdAGENTS.mdroot
Quality
80/100
Scores the file, not the repository.Length
725 words
14 headings · 7 code blocksRepository
15
— · pushed 122 days agoLast changed
3 days ago
First indexed 3 days ago.1# Agent Instructions23This project uses **bd** (beads) for issue tracking. Run `bd onboard` to get started.45## Quick Reference67```bash8bd ready # Find available work9bd show <id> # View issue details10bd update <id> --claim # Claim work atomically11bd close <id> # Complete work12bd sync # Sync with git13```1415## Non-Interactive Shell Commands1617**ALWAYS use non-interactive flags** with file operations to avoid hanging on confirmation prompts.1819Shell commands like `cp`, `mv`, and `rm` may be aliased to include `-i` (interactive) mode on some systems, causing the agent to hang indefinitely waiting for y/n input.2021**Use these forms instead:**22```bash23# Force overwrite without prompting24cp -f source dest # NOT: cp source dest25mv -f source dest # NOT: mv source dest26rm -f file # NOT: rm file2728# For recursive operations29rm -rf directory # NOT: rm -r directory30cp -rf source dest # NOT: cp -r source dest31```3233**Other commands that may prompt:**34- `scp` - use `-o BatchMode=yes` for non-interactive35- `ssh` - use `-o BatchMode=yes` to fail instead of prompting36- `apt-get` - use `-y` flag37- `brew` - use `HOMEBREW_NO_AUTO_UPDATE=1` env var3839<!-- BEGIN BEADS INTEGRATION -->40## Issue Tracking with bd (beads)4142**IMPORTANT**: This project uses **bd (beads)** for ALL issue tracking. Do NOT use markdown TODOs, task lists, or other tracking methods.4344### Why bd?4546- Dependency-aware: Track blockers and relationships between issues47- Version-controlled: Built on Dolt with cell-level merge48- Agent-optimized: JSON output, ready work detection, discovered-from links49- Prevents duplicate tracking systems and confusion5051### Quick Start5253**Check for ready work:**5455```bash56bd ready --json57```5859**Create new issues:**6061```bash62bd create "Issue title" --description="Detailed context" -t bug|feature|task -p 0-4 --json63bd create "Issue title" --description="What this issue is about" -p 1 --deps discovered-from:bd-123 --json64```6566**Claim and update:**6768```bash69bd update <id> --claim --json70bd update bd-42 --priority 1 --json71```7273**Complete work:**7475```bash76bd close bd-42 --reason "Completed" --json77```7879### Issue Types8081- `bug` - Something broken82- `feature` - New functionality83- `task` - Work item (tests, docs, refactoring)84- `epic` - Large feature with subtasks85- `chore` - Maintenance (dependencies, tooling)8687### Priorities8889- `0` - Critical (security, data loss, broken builds)90- `1` - High (major features, important bugs)91- `2` - Medium (default, nice-to-have)92- `3` - Low (polish, optimization)93- `4` - Backlog (future ideas)9495### Workflow for AI Agents96971. **Check ready work**: `bd ready` shows unblocked issues982. **Claim your task atomically**: `bd update <id> --claim`993. **Work on it**: Implement, test, document1004. **Discover new work?** Create linked issue:101 - `bd create "Found bug" --description="Details about what was found" -p 1 --deps discovered-from:<parent-id>`1025. **Complete**: `bd close <id> --reason "Done"`103104### Auto-Sync105106bd automatically syncs with git:107108- Exports to `.beads/issues.jsonl` after changes (5s debounce)109- Imports from JSONL when newer (e.g., after `git pull`)110- No manual export/import needed!111112### Important Rules113114- ✅ Use bd for ALL task tracking115- ✅ Always use `--json` flag for programmatic use116- ✅ Link discovered work with `discovered-from` dependencies117- ✅ Check `bd ready` before asking "what should I work on?"118- ❌ Do NOT create markdown TODO lists119- ❌ Do NOT use external issue trackers120- ❌ Do NOT duplicate tracking systems121122For more details, see README.md and docs/QUICKSTART.md.123124## Landing the Plane (Session Completion)125126**When ending a work session**, you MUST complete ALL steps below. Work is NOT complete until `git push` succeeds.127128**MANDATORY WORKFLOW:**1291301. **File issues for remaining work** - Create issues for anything that needs follow-up1312. **Run quality gates** (if code changed) - Tests, linters, builds1323. **Update issue status** - Close finished work, update in-progress items1334. **PUSH TO REMOTE** - This is MANDATORY:134```bash135 git pull --rebase136 bd sync137 git push138 git status # MUST show "up to date with origin"139```1405. **Clean up** - Clear stashes, prune remote branches1416. **Verify** - All changes committed AND pushed1427. **Hand off** - Provide context for next session143144**CRITICAL RULES:**145- Work is NOT complete until `git push` succeeds146- NEVER stop before pushing - that leaves work stranded locally147- NEVER say "ready to push when you are" - YOU must push148- If push fails, resolve and retry until it succeeds149150<!-- END BEADS INTEGRATION -->151
Also in TakaGoto/rag-learning-academy
Diff this repo’s formatsOne repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| TakaGoto/rag-learning-academyCLAUDE.md · 15 | CLAUDE.md | setuparchagent-behaviour | 44/100 | 3 days ago |
Similar configs
Same format, overlapping stack, ranked by quality.
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| SkeneTechnologies/skene-cookbookAGENTS.md · 51 | AGENTS.md | setupbuildtestlint-format+7 | 100/100 | 2 days ago | |
| OnlyTerp/prompt-cache-skillsAGENTS.md · 112 | AGENTS.md | setupbuildtestlint-format+5 | 100/100 | 3 days ago | |
| n8n-io/n8npackages/@n8n/agents/AGENTS.md · 199k | AGENTS.md | buildteststylearch+3 | 100/100 | 3 days ago | |
| vllm-project/vllmAGENTS.md · 88k | AGENTS.md | setuptestlint-formatstyle+5 | 100/100 | 3 days ago | |
| unoplat/unoplat-code-confluenceunoplat-code-confluence-frontend/AGENTS.md · 95 | AGENTS.md | setupbuildtestlint-format+6 | 100/100 | 2 days ago | |
| netdata/netdatasrc/go/plugin/ibm.d/AGENTS.md · 80k | AGENTS.md | buildtestlint-formatarch+3 | 99/100 | 3 days ago | |
| unoplat/unoplat-code-confluenceunoplat-code-confluence-query-engine/AGENTS.md · 95 | AGENTS.md | setupbuildtestlint-format+5 | 98/100 | 2 days ago | |
| ruvnet/RuViewAGENTS.md · 88k | AGENTS.md | teststylegitsecurity+3 | 97/100 | 3 days ago |
