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 to-specgit 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/to-spec)<a href="https://agentmods.dev/skills/tsai09495/matt-pocock-engineering/to-spec"><img src="https://agentmods.dev/badge/skills/tsai09495/matt-pocock-engineering/to-spec/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/skills/tsai09495/matt-pocock-engineering/to-spec"><img src="https://agentmods.dev/badge/skills/tsai09495/matt-pocock-engineering/to-spec.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.00712 |
| Opus 5 | $0.00023 | $0.00356 |
| Sonnet 5 | $0.00009 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
to-spec 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
To Spec
Synthesize what is already known into a buildable specification. Do not restart grilling or invent missing product decisions.
Treat legacy user wording such as “PRD” or “requirements document” as an entrance to this workflow, not as the formal artifact name. Unless the repository explicitly mandates different terminology, call the work in progress, draft, headings, destination preview, and published artifact a spec; do not say you are drafting or publishing a PRD in progress narration, and do not title the output “PRD.”
The issue-tracker convention may be configured in docs/agents/issue-tracker.md. Read it when present. Selecting this skill does not authorize publishing.
Process
- Gather the current conversation, referenced plans or tickets, repository instructions, relevant domain glossary, ADRs, and code facts.
- Separate confirmed decisions from unresolved items. If an unresolved item would materially change the spec, ask one narrow question or mark it clearly; do not silently choose.
- Identify the highest practical seams for verifying the feature. Prefer established public seams. Ask for confirmation only when a new, ambiguous, or expensive seam is proposed.
- Draft the spec using the structure below.
- Show the complete draft and summarize unresolved risks.
- Publish to the configured tracker or write a repository file only after the user approves the draft or explicitly requested that exact write in the current request.
The spec should be complete enough to cover important behavior, boundaries, failure paths, and verification without mechanically generating a long list of low-value stories.
Spec template
Problem
Describe the user's problem, current limitation, and why it matters.
Solution
Describe the intended behavior from the user's perspective and the boundaries of the solution.
User stories or behavioral outcomes
Include only distinct outcomes that clarify behavior. Use “As a … I want … so that …” when it improves precision; do not force every technical constraint into a story.
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.
- 9d ago First seen · 66 lines · 46 tokens per session scan A 181ddb856dbd
to-spec is a skill published in the GitHub repository tsai09495/matt-pocock-engineering (2 stars, last pushed 15d ago), licensed MIT. It adds 46 tokens to every session and 712 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.