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/hulupeep/specflow/specflow-auditnpx skills add Hulupeep/Specflow --skill specflow-auditgit clone --depth 1 https://github.com/Hulupeep/SpecflowWrote 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/hulupeep/specflow/specflow-audit)<a href="https://agentmods.dev/skills/hulupeep/specflow/specflow-audit"><img src="https://agentmods.dev/badge/skills/hulupeep/specflow/specflow-audit.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 | $0.00199 | $0.01467 |
| Opus 5 | $0.00100 | $0.00733 |
| Sonnet 5 | $0.00040 | $0.00293 |
| Haiku 4.5 | $0.00020 | $0.00147 |
Grade A, and why
specflow-audit 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 6d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specflow Audit & Uplift
Take a partially-compliant Specflow story (some sections present, others missing) and bring it to compliance through a fixed three-phase process. The quality comes from the process, not improvisation — never freelance the uplift inline.
When to run
Trigger on: "make specflow compliant", "specflow audit", "uplift this story / ticket", "run specflow auditor", "is this story compliant", or /specflow-audit <file-or-issue>.
Do NOT trigger on generic "make this PR/code compliant" that has nothing to do with Specflow specs.
The target is a story/ticket — a GitHub issue body, a docs/specs/*.md file, or pasted spec text. Not source code.
The non-negotiable process
Run these three phases in order. Do not skip phase 3.
Phase 1 — Gap analysis (board-auditor)
Read the target and diff it against the full Specflow template. Produce an explicit list of which sections are PRESENT and which are MISSING. The template sections are in references/uplift-process.md. Identify the ticket type (feature / bug / journey) — bug tickets legitimately N/A some sections; record the justification.
Phase 2 — Surgical uplift (specflow-uplifter)
Add only the missing sections — never rewrite or duplicate existing content. Generate executable artifacts, not prose:
- Data Contract: copy-pasteable
CREATE TABLE/CREATE FUNCTION/ RLSCREATE POLICY(use the join-through RLS pattern for tables without a direct org/owner column). - Frontend Interface: typed TypeScript hook/interface signatures matching project conventions.
- Invariants Referenced:
I-<DOMAIN>-NNNcodes; reuse existing codes, take the next free number for new ones — never invent a code that already exists. - Gherkin Scenarios, Acceptance Criteria (behaviour-only checkboxes, including negative paths), Definition of Done, and
data-testidcoverage.
Section templates and the RLS/invariant patterns are in references/uplift-process.md. Post the additions as one clearly-labelled uplift comment (GitHub) or appended block (file) — supplementing, not replacing.
What ships with it
2 files 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.
- 6d ago First seen · 70 lines · 199 tokens per session scan A c12737fb37f4
specflow-audit is a skill published in the GitHub repository Hulupeep/Specflow (25 stars, last pushed 1mo ago), licensed MIT. It adds 199 tokens to every session and 1,467 once invoked, about $0.0010 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
truecourse-analyze
Run TrueCourse architecture analysis on this repository.
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
truecourse-fix
Fix TrueCourse violations that have suggested fixes.
truecourse-list
List TrueCourse violations found in this repository.
scan
Scan a project with sentrux to get structural health grades (A-F) across 14 dimensions including coupling, cycles, cohesion, dead code, and test coverage. Use when the user wants to check code quality, architecture health, or before/after an agent session.
map
This skill should be used when the user asks to "generate architecture map", "visualize spec relationships", "create ARCHITECTURE.md", "show concept dependencies", "wyx map", or wants a Mermaid graph with dependency matrix and data flow paths derived from all wyx specs.