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.
git 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/commands/arrrrny/zuraffa/speckit.tdd.run)<a href="https://agentmods.dev/commands/arrrrny/zuraffa/speckit.tdd.run"><img src="https://agentmods.dev/badge/commands/arrrrny/zuraffa/speckit.tdd.run/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/commands/arrrrny/zuraffa/speckit.tdd.run"><img src="https://agentmods.dev/badge/commands/arrrrny/zuraffa/speckit.tdd.run.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 | $0.00043 | $0.00851 |
| Opus 5 | $0.00022 | $0.00426 |
| Sonnet 5 | $0.00009 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
speckit.tdd.run 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 5d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDD Run (zfa-delegating)
Drive every behavior in the feature's test list through
red → green → refactor. When this project is zuraffa-wired, the loop is
deterministic — dispatch to zfa tdd run. The LLM's role narrows to:
fixing the code when zfa stops at an honest RED, and handling escape hatches.
User Input
$ARGUMENTS
Accept: all (default), a behavior id, or resume.
Step 0 — Engine detection
zfa --version 2>/dev/null && test -f .zfa.json && echo "ZFA_OK" || echo "ZFA_MISSING"
ZFA_OK→ Step 1ZFA_MISSING→ fall back to the original LLM-guided loop (see "Fallback Path")
Step 1 — Resolve the feature
Standard resolution: input → .specify/feature.json → prerequisites script.
Set FEATURE_SLUG.
Step 2 — Dispatch to zfa
zfa tdd run "$FEATURE_SLUG" --timeout 25 2>&1
(Adjust --timeout for the hardware; 25 minutes per step on an Intel Mac is
the measured safe ceiling.)
Step 3 — Handle the verdict
The command runs until complete or an honest stop. Interpret:
result=complete pending=0 red=0 green=0 done=N
All behaviors done. Report: behaviors driven, suite state, evidence path
(tdd/cycle-log.md). Tick the corresponding tasks.md tasks.
result=stopped stopped_at=<behavior>:<step>
zfa stopped honestly. The stops the LLM must handle:
verify-red with classification=compile-error:
The generated test doesn't compile. This is a generator bug (or a spec
grammar edge) — report the error, fix the compile error (escaping, imports)
WITHOUT changing the test's assertions, then resume.
make with outcome=generation-error or not-certified-red:
The make path failed. Inspect the cycle-log for the reason. If the behavior's
subject needs a real implementation the generator can't express, implement
the minimal change that makes the certified-red test pass (this is the TDD
"smallest change" step — the LLM writes it, the suite proves it).
refactor with outcome=not-green or runner-error:
The suite went red during refactor. Inspect, fix, resume.
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.
- 5d ago First seen · 94 lines · 43 tokens per session scan A 650771fe0325
speckit.tdd.run is a command published in the GitHub repository arrrrny/zuraffa (5 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 851 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 2026-09-03.
Other commands, from other repositories
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.
workflow-implement
Exécuter la phase d'Implémentation - développement sprint avec TDD/BDD.
fix
Correction automatisee des bugs identifies par la QA Recette.
hatch3r-bug-pipeline
Run a known-cause bug fix through a 3-phase test-first pipeline -- reproduce + root-cause, regression-test + fix together, then root-cause-depth review -- with full sub-agent delegation.
ralph.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
feature-implement-execute
Phase 4 of develop: Execute the implementation plan with per-task TDD, quality gates, and completion verification.