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/hookdeck/agent-skills/agents-mdgit clone --depth 1 https://github.com/hookdeck/agent-skillsWhat 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 | $0.05263 | $0.05263 |
| Opus 5 | $0.02632 | $0.02632 |
| Sonnet 5 | $0.01053 | $0.01053 |
| Haiku 4.5 | $0.00526 | $0.00526 |
Grade A, and why
agent-skills 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI agents working on the Hookdeck Agent Skills repository.
Read this file before creating, modifying, or reviewing any skill in this repo.
hookdeck.com discovery index
Product skills under skills/event-gateway/, skills/hookdeck/, and skills/outpost/ are packaged at build time by the hookdeck/website repo and served from https://hookdeck.com/.well-known/agent-skills/ (RFC v0.2.0 discovery index + .tar.gz archives). When those paths change on main, .github/workflows/trigger-website-deploy.yml notifies Hookdeck, which triggers a Vercel production deploy of the site (same Hookdeck source as Outpost docs; both configured as Actions secrets: HOOKDECK_WEBSITE_DEPLOY_SOURCE_URL, VERCEL_WEBSITE_DEPLOY_HOOK_SOURCE_API_KEY). See website scripts/agent-skills-discovery.md for packaging details.
Specification
All skills MUST conform to the Agent Skills specification and follow the authoring best practices.
Hard constraints
- Every skill is a directory under
skills/containing aSKILL.mdfile SKILL.mdmust have YAML frontmatter withnameanddescriptionname: max 64 chars, lowercasea-z, numbers, and hyphens only. Must match the parent directory name exactly. No consecutive hyphens. Cannot start or end with a hyphen.description: max 1024 chars. Third person. Describes what the skill does AND when to use it with specific trigger phrases.- SKILL.md body: under 500 lines (< 5000 tokens). Move detailed content to
references/files. - File references: one level deep from SKILL.md only. SKILL.md links to reference files. Reference files may link to other reference files for workflow (e.g. 01→02→04) or "see also"; avoid long chains (A→B→C→D).
- Reference files over 100 lines: include a table of contents at the top.
- Progressive disclosure:
nameanddescriptionare loaded at startup for all skills. Full SKILL.md is loaded when the skill is activated. Reference files are loaded only on demand.
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 · 291 lines · 5,263 tokens per session scan A fa3a782f7b28
agent-skills AGENTS.md is an instructions file published in the GitHub repository hookdeck/agent-skills (5 stars, last pushed 13d ago), licensed MIT. It adds 5,263 tokens to every session, about $0.0263 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
hookdeck-cli AGENTS.md
Instructions for hookdeck/hookdeck-cli, covering agents guidelines for hookdeck cli, 1. project structure & navigation, core directories, key files and 2. openapi to cli conversion standards.
hookdeck-cli CLAUDE.md
Instructions for hookdeck/hookdeck-cli: Read AGENTS.md for all agent instructions (project structure, testing, sandbox permissions, CLI conventions, .agents/skills/ workflows, and releases).
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.
buildNext
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).
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.
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).