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.
git clone --depth 1 https://github.com/MatthewYe/autopilot-toolkitWrote 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/plugins/matthewye/autopilot-toolkit/upstream)<a href="https://agentmods.dev/plugins/matthewye/autopilot-toolkit/upstream"><img src="https://agentmods.dev/badge/plugins/matthewye/autopilot-toolkit/upstream/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/matthewye/autopilot-toolkit/upstream"><img src="https://agentmods.dev/badge/plugins/matthewye/autopilot-toolkit/upstream.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mattpocock-skills 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 9d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What it installs
The manifest is a name and a version. 37 skills travel with it, and installing the plugin installs all of them — 1,269 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ask-matt A 22 tokens
- Skill wayfinder A 46 tokens
- Skill writing-for-agents A 28 tokens
- Skill diagnosing-bugs A 40 tokens
- Skill setup-ts-deep-modules A 45 tokens
- Skill teach A 15 tokens
- Skill code-review A 94 tokens
- Skill codebase-design A 57 tokens
- Skill improve-codebase-architecture A 32 tokens
- Skill setup-matt-pocock-skills A 44 tokens
- Skill to-tickets A 54 tokens
- Skill triage A 33 tokens
- Skill writing-shape A 19 tokens
- Skill retro A 10 tokens
- Skill writing-beats A 28 tokens
- Skill domain-modeling A 35 tokens
- Skill scaffold-exercises A 45 tokens
- Skill tdd A 33 tokens
- Skill wizard A 58 tokens
- Skill writing-fragments A 16 tokens
- Skill implement-spec A 18 tokens
- Skill loop-me A 20 tokens
- Skill migrate-to-shoehorn A 48 tokens
- Skill prototype A 39 tokens
- Skill to-questionnaire A 21 tokens
- Skill to-spec A 30 tokens
- Skill grilling A 38 tokens
- Skill setup-pre-commit A 62 tokens
- Skill claude-handoff A 22 tokens
- Skill handoff A 19 tokens
- Skill research A 49 tokens
- Skill implement A 16 tokens
- Skill wait-what A 18 tokens
- Skill grill-with-docs A 30 tokens
- Skill grill-me A 14 tokens
- Skill pr A 9 tokens
- Skill git-guardrails-claude-code B 62 tokens
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago Changed 15a5a7227915
- 15d ago Changed · +2 lines 78fefd6e7346
- 1mo ago Changed e531ddc65605
- 1mo ago Changed 40d0fbf87be0
- 1mo ago First seen · 49 lines scan A 85a5f2ad87b1
mattpocock-skills is a plugin published in the GitHub repository MatthewYe/autopilot-toolkit (2 stars, last pushed 9d ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
mattpocock-skills
Matt Pocock's agent skills for real engineering: grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
openmetadata-skills
Complete AI development workflow for OpenMetadata — structured planning, TDD, code review, test enforcement (90% coverage), systematic debugging, and connector development. Includes language-specific review agents for Java, Python, and TypeScript.
superjawn
Research-augmented fork of obra/superpowers. Ships 13 workflow skills (brainstorming, planning, code review, debugging, verification, worktrees, parallel agents) standalone, with no dependency on the upstream superpowers plugin.
ring marketplace
Lerian Studio plugin marketplace: Core software engineering skills (TDD, debugging, code review), specialized developer agents (Backend, DevOps, Frontend, QA, SRE) plus 12 code-review reviewers (9 default hard-gate reviewers and 3 conditional stack specialists), product planning workflows (8-gate pre-dev system), and…
ring-default
Core skills library from the Lerian Team: TDD, code review, collaboration patterns, and proven techniques. 23 essential skills for software engineering excellence, including plan authoring and execution.
mattpocock-skills
Skills adapted from Matt Pocock's public collection.