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 skills add tsai09495/matt-pocock-engineering --skill researchgit clone --depth 1 https://github.com/tsai09495/matt-pocock-engineeringWrote 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/skills/tsai09495/matt-pocock-engineering/research)<a href="https://agentmods.dev/skills/tsai09495/matt-pocock-engineering/research"><img src="https://agentmods.dev/badge/skills/tsai09495/matt-pocock-engineering/research.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 5.1 | $0.00033 | $0.00577 |
| Opus 5 | $0.00016 | $0.00289 |
| Sonnet 5 | $0.00007 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
research 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 8d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research
Answer one bounded engineering question with auditable evidence. Default to the current agent. Background or parallel research is available only through optional-enhancements.md.
Scope
Before searching, state or infer:
- the exact question;
- what decision the answer will support;
- source and freshness requirements;
- what is explicitly outside scope.
Ask only when an ambiguity would materially change the research. Do not turn a narrow lookup into a broad market or architecture study.
Evidence hierarchy
Prefer, in order appropriate to the question:
- repository source code, tests, schemas, and pinned dependency versions;
- official documentation, specifications, standards, and first-party API references;
- upstream source code, release notes, issues, or maintainer statements;
- high-quality secondary analysis only when primary sources do not answer the question.
For mutable facts, verify against current sources. For technical questions, do not treat search snippets, generated summaries, or unsourced community claims as proof.
Method
- Inspect local repository evidence first when the question concerns the current codebase.
- Gather the smallest set of sources that can answer the question.
- Cross-check important claims that depend on interpretation or version differences.
- Record contradictions, version boundaries, and access limitations.
- Separate:
- Confirmed fact — directly supported by cited evidence;
- Inference — a reasoned conclusion from facts, labelled as such;
- Unknown — evidence is missing, contradictory, or inaccessible.
- Answer the decision question, not merely summarize sources.
Output
If the user wants only a chat answer, respond in chat and do not create a file. If the user requests durable research, or an authorized parent workflow needs an artifact, use the repository's existing research/docs convention. When no convention exists, propose a location before the first write.
What ships with it
1 file beside SKILL.md 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.
- 8d ago First seen · 71 lines · 33 tokens per session scan A 60becdd12e23
research is a skill published in the GitHub repository tsai09495/matt-pocock-engineering (2 stars, last pushed 14d ago), licensed MIT. It adds 33 tokens to every session and 577 once invoked, about $0.0002 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 skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration in proposals and decision-facing writing. Use when the user asks to rewrite or audit a proposal, plan, research contribution, executive summary, or similar text for directness. Do not use for ordinary code work or unrelated prose.