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/agent-tools-org/ai-dispatch/claude-mdgit clone --depth 1 https://github.com/agent-tools-org/ai-dispatchWhat 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 | $0.04226 | $0.04226 |
| Opus 5 | $0.02113 | $0.02113 |
| Sonnet 5 | $0.00845 | $0.00845 |
| Haiku 4.5 | $0.00423 | $0.00423 |
Grade A, and why
ai-dispatch CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-dispatch (aid)
Install
- NEVER cp binary to
/opt/homebrew/bin/— macOS provenance xattr blocks execution /opt/homebrew/bin/aidis a symlink to~/.cargo/bin/aid- Install command (MUST re-sign after copy — sandbox provenance blocks execution):
cp "$CARGO_TARGET_DIR/release/aid" ~/.cargo/bin/aid && codesign --force --sign - ~/.cargo/bin/aid
Release
Release must go through scripts/release.sh. Do not manually bump Cargo.toml, edit the top release entry in CHANGELOG.md, create the release commit, create the release tag, or push the release branch/tag by hand.
Release flow requirements:
- Start from a clean git worktree. Commit or stash local edits before running the release script.
- Prepare a Markdown notes file with one
-bullet per shipped change. - Run
scripts/release.sh --dry-run <version> <notes-file>first and review the planned commit/tag/push. - Run
scripts/release.sh <version> <notes-file>for the actual release. - Treat any direct
git tag, manual version bump, or manual changelog-only release edit as an invalid release flow.
cat > /tmp/aid-release-notes.md <<'EOF'
- Short release summary
- Additional shipped change
EOF
scripts/release.sh --dry-run 8.75.0 /tmp/aid-release-notes.md
scripts/release.sh 8.75.0 /tmp/aid-release-notes.md
Official Guide Maintenance
default-skills/aid-guide/ is the release-managed, authoritative AID operating
guide. Any change to a public command, flag, lifecycle transition, safety
invariant, configuration key, or recommended workflow must update the relevant
guide reference in the same commit. Keep references/command-index.md
complete. Run:
python3 ~/.codex/skills/.system/skill-creator/scripts/quick_validate.py \
default-skills/aid-guide
cargo test --test aid_guide_e2e --test init_e2e
Run
Dispatch a task to an AI agent. Core command — most other features build on this.
aid run codex "Add unit tests" --verify # with auto-verify
aid run gemini "Research topic" -o notes.md # research with output file
aid run codex "Refactor" -w feat/refactor --bg # background + worktree
aid advise "implement feature" --difficulty moderate --budget standard --urgency normal --rigor standard
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 · 375 lines · 4,226 tokens per session scan A 24a16d1a9d6f
ai-dispatch CLAUDE.md is an instructions file published in the GitHub repository agent-tools-org/ai-dispatch (11 stars, last pushed 14d ago), licensed MIT. It adds 4,226 tokens to every session, about $0.0211 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
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.