speckit-spec-stats-report

speckit-spec-stats-report is a skill for Claude Code from arrrrny/zuraffa. It costs 78 tokens per session (573 once invoked), scanned A, original, MIT.

A project dashboard generator that scans feature specification folders and summarizes their development stages and progress. TDD means test-driven development, where tests guide implementation; when its files are present, the dashboard includes related test progress.

In plain words
What is it for?
Use it to create a Markdown project report, print a JSON snapshot, or render a report from an existing snapshot file.
Why use it?
It gives you one view of which features are specified, planned, being built, or complete, and where work may be stale. It can also produce machine-readable JSON for other tools.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: installed under .agents/ (shared by several agents).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .specify/extensions/spec-stats/scripts/spec-stats.mjs report.

Good fit Use it to create a Markdown project report, print a JSON snapshot, or render a report from an existing snapshot file.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/arrrrny/zuraffa
agentmods
npx agentmods add skills/arrrrny/zuraffa/speckit-spec-stats-report

Made for: Claude Code.

Wrote 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.

agentmods badge for speckit-spec-stats-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-spec-stats-report/github.svg)](https://agentmods.dev/skills/arrrrny/zuraffa/speckit-spec-stats-report)
Your own site
<a href="https://agentmods.dev/skills/arrrrny/zuraffa/speckit-spec-stats-report"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-spec-stats-report/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.

agentmods 80×15 button for speckit-spec-stats-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/arrrrny/zuraffa/speckit-spec-stats-report"><img src="https://agentmods.dev/badge/skills/arrrrny/zuraffa/speckit-spec-stats-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 573 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.00573
Opus 5 $0.00039 $0.00287
Sonnet 5 $0.00016 $0.00115
Haiku 4.5 $0.00008 $0.00057

Measured 11d ago against content hash 17b4ded06a3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

speckit-spec-stats-report 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.

.agents/skills/speckit-spec-stats-report/SKILL.md · 41 lines

What it actually says

Spec Stats — Report

Generate the spec portfolio dashboard for the current project.

User Input

$ARGUMENTS

Optional flags:

  • --json — print the machine-readable stats.json to stdout (no files written)
  • --out <path> — write the markdown dashboard to this path (overrides config output_path)
  • --render --in <stats.json> — render an existing snapshot instead of re-scanning

Execution

Run the bundled Node engine from the repository root:

node .specify/extensions/spec-stats/scripts/spec-stats.mjs report
# or: node .specify/extensions/spec-stats/scripts/spec-stats.mjs report --json
# or: node .specify/extensions/spec-stats/scripts/spec-stats.mjs report --out /tmp/stats.md

The engine:

  1. Lists every specs/<NNN>-<slug>/ directory.
  2. Detects each feature's stage (specified → planned → tasked → implementing → complete) from file presence and tasks.md checkbox counts.
  3. Detects whether the TDD extension is installed in this project (.specify/memory/tdd-profile.md or .specify/extensions/tdd). When installed, it reads each feature's tdd/test-list.md and renders the TDD Deep Stats table with columns: #, feature, A (acceptance behaviors), U (unit behaviors), char (characterization behaviors), DONE (behaviors in DONE state), loop (full / outer-only / inside-out / absent), and tasks.md (updated when TDD markers are present, else absent), plus a totals row.
  4. Writes the dashboard to output_path (default .specify/stats/SPEC-STATS.md) and a stats.json snapshot beside it.

Report the output path (or the JSON) back to the user. This command is read-only — it never modifies specs, tasks, or code.

Changes

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.

  1. 11d ago First seen · 41 lines · 78 tokens per session scan A 17b4ded06a3b

Subscribe to this mod's changes

speckit-spec-stats-report is a skill published in the GitHub repository arrrrny/zuraffa (5 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 573 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.