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/ostin-pil/aboard/claude-mdgit clone --depth 1 https://github.com/ostin-pil/aboardWrote 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/ostin-pil/aboard/claude-md)<a href="https://agentmods.dev/instructions/ostin-pil/aboard/claude-md"><img src="https://agentmods.dev/badge/instructions/ostin-pil/aboard/claude-md.svg" alt="Measured on agentmods" 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 | $0.05827 | $0.05827 |
| Opus 5 | $0.02913 | $0.02913 |
| Sonnet 5 | $0.01165 | $0.01165 |
| Haiku 4.5 | $0.00583 | $0.00583 |
Grade A, and why
aboard CLAUDE.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 4d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
aboard
An agent-first board of falsifiable claims about systemic problems facing humanity. Three modules over a shared claim graph: predictions (time-boxed forecasts), problem trees (symptom → mechanism → leverage point), and adversarial debates (steel-manned dual-dossier with ranked cruxes). Every claim is published as machine-readable JSON-LD by default.
Run
npm install
npm run dev # http://localhost:3000
npm run build # production build (full type-check)
npx tsc --noEmit # type-check only, faster
npm run lint # eslint; session-end and CI both gate on it (only reader of .js/.mjs)
npm run test # vitest
npm run lint:resolution # forecast resolution-criteria rigor; session-end and CI gate on --strict
npm run typecheck:mcp # mcp-server/, which the root tsconfig excludes
npm run typecheck:clients # clients/, likewise excluded
npm run check:built-urls # asserts over out/; run it after a build
npm run check:config # ci.yml + wrangler.jsonc; the only reader either has
npm run check:exports # knip; dead exports, which nothing else in the gate sees
shellcheck $(git ls-files '*.sh') # shell scripts; session-end and CI both gate on it
lint:resolution reports forecasts a distrustful reader could not settle: criteria resolving on an utterance, criteria with no checkable threshold, and forecasts with no resolutionSource. Forecasts marked supersededBy are skipped and listed — their criteria are historical record, repaired by the replacements they name. Warn-only by default and outside npm run build, but the session-end gate runs it with --strict (build_commands in .claude/lifecycle-manifest.md), so a session cannot land a forecast a distrustful reader could not settle.
The repo's two shell scripts are bin/check-prose.sh, which is the prose gate itself, and scripts/publish-registry.sh, which handles a signing key and writes to a public registry. Both are executable behaviour that no Node command here can reach, so shellcheck runs in build_commands and as the first step in CI. That is also why "*.sh" is in code_globs: the classification only means something because a shell-aware command sits behind it.
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.
- 4d ago First seen · 230 lines · 5,827 tokens per session scan A ba59747d7204
aboard CLAUDE.md is an instructions file published in the GitHub repository ostin-pil/aboard (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 5,827 tokens to every session, about $0.0291 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
reliefweb-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/reliefweb-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
reliefweb-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/reliefweb-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).