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 arrrrny/zuraffa --skill speckit-tdd-verifygit clone --depth 1 https://github.com/arrrrny/zuraffaWrote 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/arrrrny/zuraffa/speckit-tdd-verify)<a href="https://agentmods.dev/skills/arrrrny/zuraffa/speckit-tdd-verify"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-tdd-verify/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/arrrrny/zuraffa/speckit-tdd-verify"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-tdd-verify.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 | $0.00038 | $0.00636 |
| Opus 5 | $0.00019 | $0.00318 |
| Sonnet 5 | $0.00008 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
speckit-tdd-verify 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 7d 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.
What it actually says
TDD Verify (zfa-delegating)
Audit the feature's TDD discipline and test strength. When this project is
zuraffa-wired, the audit is deterministic — dispatch to zfa tdd verify.
User Input
$ARGUMENTS
Accept: --no-tasks (don't append remediation tasks on FAIL).
Step 0 — Engine detection
zfa --version 2>/dev/null && test -f .zfa.json && echo "ZFA_OK" || echo "ZFA_MISSING"
ZFA_OK→ Step 1ZFA_MISSING→ fall back to the original LLM-guided audit
Step 1 — Resolve the feature
Standard resolution: input → .specify/feature.json → prerequisites script.
Step 2 — Dispatch to zfa
zfa tdd verify --feature "$FEATURE_SLUG" 2>&1
Step 3 — Interpret the verdict
zfa writes FEATURE_DIR/tdd/verification.md with a gate verdict.
Gate passed (exit 0)
Report: killed/survived/timed_out mutant counts, restoration verified, the verification path. Feature's TDD discipline is proven.
Gate preflight_red (non-zero)
The suite is red — verify refuses to audit a red suite (correct gate).
Report the failing tests, send the user back to /speckit.tdd.run.
Mutation survived (exit 1)
At least one mutant survived — a test is weak. Report the per-mutant table
from verification.md with the --> fix: pointer to the weak test. Unless
--no-tasks, append remediation tasks to tasks.md (one per surviving
mutant: "strengthen to kill ").
Exit 2 or 3
Grammar or contract drift. Report verbatim.
Step 4 — Remediation loop (when FAIL)
- Append remediation tasks to
tasks.md(one per finding). - Drive them through
/speckit.tdd.run(they pick up as new behaviors). - Re-run this command.
- Cap: 3 remediation passes; report the verdict each pass.
Fallback Path (non-zuraffa projects)
Run the original LLM-guided audit: check test-first evidence in git history, red-phase evidence in cycle-log, test-smell rubric, mutation testing on changed files, acceptance-criteria coverage; write verification.md with verdict and remediation tasks.
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.
- 7d ago Changed · +78 lines · +38 tokens per session 9ea126a813ae
- 8d ago Changed · -261 lines · -68 tokens per session 822accb79920
- 12d ago First seen · 262 lines · 68 tokens per session scan A c12151c1fb13
speckit-tdd-verify is a skill published in the GitHub repository arrrrny/zuraffa (5 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 636 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
compose:tdd
Use when implementing any feature or bugfix, before writing implementation code.
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.
common-tdd
Guides quality-first TDD for new behavior, bug fixes, and test changes. Selects the smallest test layer, proves a distinct regression risk, and runs bounded RED-GREEN-REFACTOR verification.
tdd-cycle
Execute full TDD red-green-refactor cycle with validation gates. Use when saying "TDD cycle", "test-driven development", or "full TDD workflow".
implement
Implement a technical design by decomposing it into dependency-ordered vertical slices, executing each with TDD red-green, reviewing each via an isolated sub-agent, and persisting progress to a state file so work survives session restarts. Use when the user has a tech design (doc or settled conversation) and says…