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/willackerly/rebar/agents-mdgit clone --depth 1 https://github.com/willackerly/rebarWhat 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 | $0.01577 | $0.01577 |
| Opus 5 | $0.00788 | $0.00788 |
| Sonnet 5 | $0.00315 | $0.00315 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
rebar AGENTS.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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — working on rebar itself
rebar v3.0.0-beta.2 | Tier 3: ENFORCED — this repo dogfoods its own methodology.
Read Before Coding
Cold Start Quad (every session, every agent, no exceptions):
README.md— universal orientationQUICKCONTEXT.md— current state (verify againstgit log --oneline -10)TODO.md— task list + pointer to INVENTORY.md (canonical planning surface)AGENTS.md(this file) — norms, contracts, collaboration
Then, before your first substantive action:
5. .claude-memory-commits/working-agreements/ — how this maintainer wants an
agent to operate here. Six short files; read all of them. They are the
collaboration contract, not architecture, and they are checked in precisely
so they survive a machine move, a tool change, or a different agent.
Reference:
DESIGN.md— the philosophy (contracts are the operating system).claude-memory-commits/environment/— MCP/ASK debugging gotchas, indexed by symptomarchitecture/CONTRACT-REGISTRY.md— contract indexarchitecture/CONTRACT-*.md— current contracts (S1-STEWARD, S2-ASK-CLI, S3-MCP-SERVER)practices/— orchestration, session lifecycle, red team, fidelity, e2efeedback/INVENTORY.md— vote-shaped accumulator + Maintainer Queue
Core Tenets
- Eat your own dog food. Every change to rebar's methodology must hold up when applied to the rebar repo itself. If the cookie-cutter template would produce a structure rebar doesn't follow, fix the template AND rebar.
- Mechanical over manual. When you find yourself doing the same drift fix
by hand, ship a script that catches it next time (
check-doc-refs.sh,check-decay-patterns.sh,sync-bootstrap.share recent examples). - One canonical planning surface.
feedback/INVENTORY.mdis the index. Don't recreate parallel planning docs at root — append to INVENTORY.
Agent Autonomy
Maximum autonomy granted. Act decisively. Ship code. Don't ask permission for routine work.
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 · 133 lines · 1,577 tokens per session scan A 13847bae37ea
rebar AGENTS.md is an instructions file published in the GitHub repository willackerly/rebar (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 1,577 tokens to every session, about $0.0079 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 2026-08-31.
Other instructions, from other repositories
pocketpaw CLAUDE.md
Instructions for pocketpaw/pocketpaw, covering claude.md, project overview, knowledge base, search the kb from terminal and show a specific module's wiki.
ai-platform-engineering AGENTS.md
Instructions for caipe-io/ai-platform-engineering, covering agent instructions, project structure, find the canonical implementation, documentation and docs & spec rules.
MultiGen CLAUDE.md
Instructions for lingyuanli/MultiGen, covering claude.md, architecture, development commands, full stack (docker) and api (local).
fluent AGENTS.md
Instructions for mrinalwadhwa/fluent, covering instructions for coding agents, fluent workflow, commit messages, subject line and body.
jarvis CLAUDE.md
Instructions for pguilp25/jarvis, covering claude.md, what jarvis is, commands, run the agent and records carry kind=draft|final + the plan text}.
pocketpaw AGENTS.md
Instructions for pocketpaw/pocketpaw, covering agents.md, agent identity, supported backends, capabilities and file system.