gastownhall/beads is a command-line graph issue tracker that gives coding agents persistent, structured memory through a dependency-aware task database. It is for developers and AI agents handling long-running work across tasks, branches, and sessions. The catalogue entries provide integrations and workflows for operating Beads with coding agents.
Borrowing it
Nothing to install: this file belongs to gastownhall/beads. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gastownhall/beads/main/AGENTS.mdgit clone --depth 1 https://github.com/gastownhall/beadsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/gastownhall/beads/agents-md)<a href="https://agentmods.dev/instructions/gastownhall/beads/agents-md"><img src="https://agentmods.dev/badge/instructions/gastownhall/beads/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/gastownhall/beads/agents-md"><img src="https://agentmods.dev/badge/instructions/gastownhall/beads/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02983 | $0.02983 |
| Opus 5.5 | $0.01193 | $0.01193 |
| Sonnet 5.5 | $0.00597 | $0.00597 |
| Haiku 4.5 | $0.00298 | $0.00298 |
Grade C, and why
beads AGENTS.md scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Agents cannot answer prompts. Use `cp -f`, `mv -f`, `rm -f`, `rm -rf`, How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beads — Contributor Agent Instructions
This file is for agents and humans developing beads (bd). If you are
using bd to track work in your own project, read the user docs instead:
docs site and
IDE and agent setup.
Nested AGENTS.md files hold area-specific rules; the routing table at the
end lists them. CLAUDE.md files are symlinks to their sibling AGENTS.md.
How work flows here
GitHub Issues is the public tracker. Use an issue when it adds context reviewers need: a user-visible bug, a behavior or design change worth discussing, or work that spans several PRs. The issue carries the reproduction, impact, and evidence for a bug, or the motivation, impact, risk, and verification plan for a change. Small, self-explanatory changes (typos, flaky tests, refactors, CI or docs tweaks) can go straight to a PR whose body explains the why.
- If the change warrants an issue, find or file one with the bug or feature form. It does not need maintainer approval first; file it before or alongside the PR.
- Work on a branch, open a PR against
main(its body saysCloses #<issue>when there is one), and let CI and review run. - Maintainers triage issues with
status/needs-triage,status/needs-info,status/needs-repro,status/needs-design, andstatus/accepted(confirmed); see CONTRIBUTING.md.
Maintainers also keep an internal bd ledger. It is optional for contributors and not a substitute for the GitHub issue.
Agent contribution policy
- File an issue when the change warrants one (see above). When you do, use
the bug or feature form fields, fill each from evidence, and answer
NOT_ENOUGH_INFOwhere the evidence runs out. - A human reviews and stands behind every issue and PR an agent drafts. Evidence that the change works end-to-end is required; "unit tests pass" alone is not evidence.
- Before implementing work, opening a PR, or merging/closing a PR, run the PR
preflight:
The preflight is the agent gate for PR handling; do not rely on auto-discovery of CONTRIBUTING.md.scripts/pr-preflight.sh --search "<topic keywords>" --repo gastownhall/beads scripts/pr-preflight.sh <pr-number> --repo gastownhall/beads - Use
ghfor GitHub issues and PRs, not browser tools. Write PR, issue, comment, and review bodies to a file, runscripts/gh-body-lint <body-file>, and pass the file withgh ... --body-file. Sign agent-written GitHub comments and reviews per engdocs/AGENT_SIGNING.md.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago Changed · +13 lines · +251 tokens per session 0f6efe3f7fba
- 9d ago Changed · +3 lines · +63 tokens per session 4b7397eae26c
- 10d ago Changed · -99 lines · -250 tokens per session d6cad0b6eb28
- 14d ago Changed · +18 tokens per session 48f0f55a03c8
- 1mo ago First seen · 291 lines · 2,901 tokens per session scan C 5aa99bf25f08
beads AGENTS.md is an instructions file published in the GitHub repository gastownhall/beads (27,917 stars, last pushed today), licensed MIT. It adds 2,983 tokens to every session, about $0.0119 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).