Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/gastownhall/beads/copilot-instructionsgit clone --depth 1 https://github.com/gastownhall/beadsWhat 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 | $0.01258 | $0.01258 |
| Opus 5 | $0.00629 | $0.00629 |
| Sonnet 5 | $0.00252 | $0.00252 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
beads copilot-instructions.md scanned grade A with 0 findings 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions for Beads
Project Overview
beads (command: bd) is a Dolt-powered issue tracker designed for AI-supervised coding workflows. Git integration is optional. We dogfood our own tool for all task tracking.
Key Features:
- Dependency-aware issue tracking
- Auto-sync via Dolt-native replication
- AI-optimized CLI with JSON output
- Dolt server mode for background operations
- MCP server integration for Claude and other AI assistants
Tech Stack
- Language: Go 1.21+
- Storage: Dolt (version-controlled SQL database)
- CLI Framework: Cobra
- Testing: Go standard testing + table-driven tests
- CI/CD: GitHub Actions
- MCP Server: Python (integrations/beads-mcp/)
Coding Guidelines
Testing
- Always write tests for new features
- Use
t.TempDir() in Go teststo avoid polluting production database - Run
go test -short ./...before committing - Never create test issues in production DB (use temporary DB)
Code Style
- Run
make ci-pr-lintbefore committing changes to Go or lint-controlled files - Follow existing patterns in
cmd/bd/for new commands - Add
--jsonflag to all commands for programmatic use - Update docs when changing behavior
Git Workflow
- Install git hooks:
bd hooks install - Use
bd dolt push/bd dolt pullfor remote sync - Before implementing related work, opening a PR, or merging/closing a PR, run:
scripts/pr-preflight.sh --search "<topic>" --repo gastownhall/beadsorscripts/pr-preflight.sh <pr-number> --repo gastownhall/beads - External contributor PRs have priority: build on them when possible, preserve tests and attribution, and never close or replace them silently.
Issue Tracking with bd
CRITICAL: This project uses bd for ALL task tracking. Do NOT create markdown TODO lists.
Essential Commands
# Find work
bd ready --json # Unblocked issues
bd stale --days 30 --json # Forgotten issues
# Create and manage (ALWAYS include --description)
bd create "Title" --description="Detailed context" -t bug|feature|task -p 0-4 --json
bd update <id> --claim --json
bd close <id> --reason "Done" --json
# Search
bd list --status open --priority 1 --json
bd show <id> --json
# Sync (if remote configured)
bd dolt push # Push to Dolt remote
bd dolt pull # Pull from Dolt remote
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.
- yesterday First seen · 139 lines · 1,258 tokens per session scan A 182267d05863
beads copilot-instructions.md is an instructions file published in the GitHub repository gastownhall/beads (26,754 stars, last pushed yesterday), licensed MIT. It adds 1,258 tokens to every session, about $0.0063 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
yaks AGENTS.md
Instructions for mattwynne/yaks, covering architecture, testing layers, mutation testing, cli design philosophy and development workflow.
lineark CLAUDE.md
Instructions for flipbit03/lineark, covering claude.md — lineark, what is this, workspace layout, key commands and writing online tests: the three pillars.
blz AGENTS.md
Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.
moo-tasks AGENTS.md
Instructions for dizlexic/moo-tasks, covering agents.md, 1. what is the moo tasks board?, 2. connecting your agent, 3. available mcp tools and 4. recommended workflow for agents.
skill-harness AGENTS.md
Instructions for 45ck/skill-harness, covering skill harness, beads issue tracker, quick reference, rules and session completion.
agentor CLAUDE.md
Instructions for lonetis/agentor, covering agent orchestrator (agentor), architecture, detailed documentation, tech stack and dev commands.