Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/arrrrny/zuraffanpx agentmods add skills/arrrrny/zuraffa/speckit-spec-stats-runsWrote 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-spec-stats-runs)<a href="https://agentmods.dev/skills/arrrrny/zuraffa/speckit-spec-stats-runs"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-spec-stats-runs/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-spec-stats-runs"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-spec-stats-runs.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 | $0.00074 | $0.00426 |
| Opus 5 | $0.00037 | $0.00213 |
| Sonnet 5 | $0.00015 | $0.00085 |
| Haiku 4.5 | $0.00007 | $0.00043 |
Grade A, and why
speckit-spec-stats-runs 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 11d 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
Spec Stats — Runs
Execute the verified test suite for one or more specs and record the result.
User Input
$ARGUMENTS
Accepted forms:
- (nothing) — run for the active feature (from
.specify/feature.json) <spec><spec>… — run for the named spec directories--all— run for every spec directory--dry-run— print what would run without executing anything
Execution
node .specify/extensions/spec-stats/scripts/spec-stats.mjs runs
# or: node .specify/extensions/spec-stats/scripts/spec-stats.mjs runs --all --dry-run
# or: node .specify/extensions/spec-stats/scripts/spec-stats.mjs runs specs/003-user-auth
The engine:
- Reads the verified full-suite command from
.specify/memory/tdd-profile.md. If absent, it stops and tells the user to run/speckit.tdd.setup— it never invents a command. - Runs that command inside each selected spec directory.
- Captures pass/fail, duration (ms), and the last 5 lines of output.
- Appends a bounded record to
.specify/stats/runs.json.
This is the only Spec Stats command that executes project commands. Honors --dry-run and never mutates a spec or its 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.
- 11d ago First seen · 40 lines · 74 tokens per session scan A 155089024bd2
speckit-spec-stats-runs is a skill published in the GitHub repository arrrrny/zuraffa (5 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 426 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 2026-08-31.
Other skills, from other repositories
fl-testing
Writes unit and widget tests for blocs, repositories, and screens using bloctest + mocktail.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
dd-triage-flaky-test
Load when investigating a specific flaky test. Gets history, failure pattern, and category, then recommends fix, quarantine, or escalate.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
security-test
Fast, continuous DevSecOps pipeline for Pull Requests and active branches. Runs SAST, SCA, and secrets detection to catch vulnerabilities before they merge.
confirm-failures-are-causally-linked-to-the-task-before-reportin
When delegating a task affected by this skill, include.