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/guidenpx skills add assisjp/specflow --skill guidegit 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 | $0.00142 | $0.00815 |
| Opus 5 | $0.00071 | $0.00407 |
| Sonnet 5 | $0.00028 | $0.00163 |
| Haiku 4.5 | $0.00014 | $0.00081 |
Grade A, and why
guide 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specflow guide
Route the user to the right skill. Do not do the work — name the next skill, say why, and stop.
The flow
grill ──▶ to-spec ──▶ to-tickets ──▶ spec-execution ──▶ human review ──▶ merge
│ (decision (only if │
└ domain-modeling log) too big └ calls tdd + code-review,
(grill docs) for 1 PR) under repo-hardening's gates
session-handoff ─ when you must stop mid-work
Route by situation
| The user is… | Run | Why |
|---|---|---|
| unsure about a plan / decision, wants it stress-tested | grill (grill docs to also capture glossary + ADRs) |
resolve ambiguity before code exists |
| pinning down domain terms or recording an architectural decision | domain-modeling | owns CONTEXT.md and ADRs |
| done deciding, wants the spec written | to-spec | synthesise the decision log into a published spec |
| holding a spec too big for one PR | to-tickets | slice into dependency-ordered tickets |
| setting up a repo for agent work (no linter/tests/CI) | repo-hardening | install the deterministic gate; write canonical commands |
| ready to build one spec/ticket into a PR | spec-execution | one spec → one reviewable PR, closed scope + evidence |
| building a feature/fix test-first | tdd | the red → green loop (usually invoked by spec-execution) |
| wanting a diff reviewed | code-review | two-axis Standards + Spec review |
| forced to stop mid-work | session-handoff | ephemeral handoff with git state for the next session |
Rules
- Name exactly one skill — the next one, not the whole chain. The flow advances one step at a time.
- If the repo has no verification block (in
AGENTS.mdorCLAUDE.md) and the user wants to build, route torepo-hardeningfirst —spec-executionrefuses to run without it. - If the source carries a
returnedmarker (areturnedlabel, or aReturned:line) and the defect is not yet resolved, route togrill— the source is defective; heal the thinking first. - If the marker is present but the user says the source is already rewritten, route to
to-spec(spec) orto-tickets(ticket — its single-ticket healing mode) to republish it, which clears the marker — thereturnedlabel on a tracker, theReturned:line locally — and releases the gate. In neither case doesspec-executionrun yet — republishing clears the marker;guide, the user, andspec-executiondo not. - If the user already named a skill, don't second-guess it — just confirm it fits and let them run it.
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 · 41 lines · 0 tokens per session scan A f097ac685f23
guide is a skill published in the GitHub repository assisjp/specflow (17 stars, last pushed 22d ago), licensed MIT. It adds 142 tokens to every session and 815 once invoked, about $0.0007 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…