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 skills/assisjp/specflow/to-specnpx skills add assisjp/specflow --skill to-specgit clone --depth 1 https://github.com/assisjp/specflowWhat 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 | $0.00083 | $0.01424 |
| Opus 5 | $0.00042 | $0.00712 |
| Sonnet 5 | $0.00017 | $0.00285 |
| Haiku 4.5 | $0.00008 | $0.00142 |
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 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
To Spec
Take the current conversation and codebase understanding and produce a spec. Do not interview the user — that is grill's job, and it should already have happened. This skill only synthesises what is already decided.
If a grill decision log exists in the conversation, it is your primary source: every decision in the spec should trace back to a log entry or to something the user explicitly said. Do not invent requirements the grilling did not settle.
Process
1. Understand the code
Explore the repo to understand its current state, if you have not already. Use the project's domain glossary (CONTEXT.md) vocabulary throughout the spec, and respect any ADRs in the area you are touching. If a term in the conversation conflicts with the glossary, resolve it before writing — a spec that uses words loosely produces code that does the wrong thing precisely.
2. Sketch the test seams
Sketch the seams at which the feature will be tested. Prefer existing seams to new ones, and prefer the highest seam possible — the fewer seams across the codebase, the better, and the ideal is one. If a new seam is needed, propose it at the highest point you can.
Check with the user that these seams match their expectations before writing the spec. This is the one place to pause — everything else is synthesis.
3. Write and publish
Write the spec using the template below, then publish it. Where it goes depends on what the project has:
- A real issue tracker (GitHub, Linear, …) — publish as one issue. On GitHub use
gh issue create. Apply aready-for-agentlabel if the project uses one. - No tracker — write it to
docs/specs/<feature-slug>.mdand commit it. A spec is durable, not scratch:spec-executionreads it in a later session, the second-failure rule assumes it survives, and a fresh clone must still find it. Never write a spec to.scratch/— that directory is ephemeral and git-ignored (ADR 0002, 0006).
If you cannot tell which the project uses, ask — it is a one-line decision, not an interview.
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.
- 2d ago First seen · 90 lines · 83 tokens per session scan A f67347d680e4
to-spec is a skill published in the GitHub repository assisjp/specflow (17 stars, last pushed 23d ago), licensed MIT. It adds 83 tokens to every session and 1,424 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…