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/maless88/roadboard/agents-mdgit clone --depth 1 https://github.com/Maless88/RoadboardWhat 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 | $0.00880 | $0.00880 |
| Opus 5 | $0.00440 | $0.00440 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
Roadboard 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 2d 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.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@CLAUDE.md
Codex / ChatGPT Analyst startup
This project uses Codex/ChatGPT primarily as an Analyst and Claude Code as the Architect/Worker coordinator.
The Analyst is a review gate, not a planning-brief producer. It reviews Worker
prompts the Architect has drafted in tasks/todo/ and returns a verdict by editing
the prompt in place — updating its frontmatter status and appending one round to
its ## Review log. It does not write separate brief files and does not move
lifecycle files.
At the start of each new session or chat, before answering "what is there to do?" or proposing work, Codex must verify the current project state:
- Read
CLAUDE.mdenough to apply the project workflow. - Check RoadBoard for open phases/tasks when RoadBoard tools are available.
- Inspect
PLAN.mdfor unchecked tasks and active milestones. - Inspect task folders:
tasks/todo/contains prompts in the draft/review/approved lifecycle; check frontmatterstatuson each.tasks/run/contains Worker prompts in progress.tasks/done/contains Worker prompts declared complete.
- Run
git status --shortbefore making claims about repository state.
To list which tasks/todo/ prompts are approved (spawnable) vs pending review:
pnpm agent:workflow ready
Analyst review protocol
When the Architect submits a prompt for review (sets status: in-review), the Analyst:
- Reads the prompt file in
tasks/todo/. - Verifies it against RoadBoard (when available),
PLAN.md, docs, and source code. Does not trust the prompt's own claims. - Checks: correctness, completeness, unambiguity, scope cleanliness, safety.
- Writes a verdict by setting frontmatter
statustoapprovedorchanges-requested, and appends one## Review loground — never overwrites prior rounds.
Default to changes-requested when uncertain. Approval is earned, not assumed.
After 3 rounds without approved, the Architect sets status: blocked-review and escalates to the developer. The Analyst does not ping-pong indefinitely.
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.
- 2d ago First seen · 68 lines · 880 tokens per session scan A 925e4ebb6a7a
Roadboard AGENTS.md is an instructions file published in the GitHub repository Maless88/Roadboard (2 stars, last pushed 17d ago), licensed MIT. It adds 880 tokens to every session, about $0.0044 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
boardstate AGENTS.md
Instructions for 100yenadmin/boardstate, covering agents & boardstate, 1. give any ai the board (@boardstate/mcp), the tool catalog, conventions for board-building agents and 2. embed a chat agent in your host (@boardstate/agent).
printyourduck-mcp AGENTS.md
AGENTS.md instructions for printyourduck/printyourduck-mcp, covering agent guide, product boundary, commands, repo ownership and release truth.
mcpqueen AGENTS.md
AGENTS.md instructions for mcpqueen/mcpqueen, covering mcp queen repository instructions, product integrity, working tree, routine autonomous work and manual gates.
mcp-hub CLAUDE.md
Claude Code instructions for ftaricano/mcp-hub, covering claude.md -- mcp-hub, o que e, stack & estrutura, como rodar / validar and setup.
mcp-hub AGENTS.md
AGENTS.md instructions for ftaricano/mcp-hub: As regras operacionais deste repo sao canonicas em CLAUDE.md (fonte unica para Claude/Codex/Hermes). Leia-o antes de tocar em codigo.
MCPs copilot-instructions.md
Copilot instructions for AceDataCloud/MCPs, covering copilot sync instructions for acedatacloud mcps, repository structure, source of truth, what to sync and rules.