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 racecraft-lab/Paddock --skill speckit-retrospective-analyzegit clone --depth 1 https://github.com/racecraft-lab/PaddockWrote 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/racecraft-lab/paddock/speckit-retrospective-analyze)<a href="https://agentmods.dev/skills/racecraft-lab/paddock/speckit-retrospective-analyze"><img src="https://agentmods.dev/badge/skills/racecraft-lab/paddock/speckit-retrospective-analyze/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/racecraft-lab/paddock/speckit-retrospective-analyze"><img src="https://agentmods.dev/badge/skills/racecraft-lab/paddock/speckit-retrospective-analyze.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 | $0.00027 | $0.01644 |
| Opus 5 | $0.00014 | $0.00822 |
| Sonnet 5 | $0.00005 | $0.00329 |
| Haiku 4.5 | $0.00003 | $0.00164 |
Grade A, and why
speckit-retrospective-analyze 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- speckit-retrospective-analyze — 98% identical, 7 lines differ
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Consider user input before proceeding (if not empty).
Goal
Analyze completed implementation against spec.md, plan.md, and tasks.md to measure spec adherence and drift. Generate actionable insights for future SDD cycles.
Constraints
- Output: Generates and saves
retrospective.mdreport to FEATURE_DIR - Post-Implementation: Run after implementation complete; warn if <80% tasks done, confirm before proceeding if <50%
- Human Gate for spec changes: before any action that modifies
spec.md(including/speckit.specifyhandoff), explicitly ask for user confirmation and stop if not approved - Confirmation policy: default is NO. Only explicit approvals (
y,yes,si,s,sí) count as consent
Execution Steps
1. Initialize Context
Run .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks from repo root. Parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive paths: SPEC, PLAN, TASKS = FEATURE_DIR/{spec,plan,tasks}.md. Abort if missing.
For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'''m Groot' (or double-quote if possible: "I'm Groot").
2. Validate Completeness
total_tasks=$(grep -c '^- \[[ Xx]\]' "$TASKS" || echo 0)
completed_tasks=$(grep -c '^- \[[Xx]\]' "$TASKS" || echo 0)
if [ "$total_tasks" -eq 0 ]; then
echo "No tasks found in $TASKS" && exit 1
fi
completion_rate=$((completed_tasks * 100 / total_tasks))
Completion thresholds:
-
=80%: Proceed with full retrospective
- 50-79%: Warn about incomplete implementation, continue with partial analysis
- <50%: STOP and confirm before continuing
3. Load Artifacts
spec.md: FR-XXX, NFR-XXX, SC-XXX, user stories, assumptions, edge casesplan.md: Architecture, data model, phases, constraints, dependenciestasks.md: All tasks with status, file paths, blockers- constitution:
.specify/memory/constitution.md(if exists)
4. Discover Implementation
- Extract file paths from completed tasks plus recent git history
- Inventory: Models, APIs, Services, Tests, Config changes
- Audit: Libraries, frameworks, integrations actually used
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.
- 12d ago First seen · 198 lines · 27 tokens per session scan A 9bb2989712e9
speckit-retrospective-analyze is a skill published in the GitHub repository racecraft-lab/Paddock (12 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 1,644 once invoked, about $0.0001 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
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
unleash
Run as a named worker draining the task queue in my private coordination repo, where each task is a GitHub Issue — claim one task at a time, check blocked-by dependencies, plan with explicit assumptions, execute, validate against acceptance criteria, and record results as comments; then stay in ambush behind a…
init
Stand up a kraken coordination repo end to end — verify or create the private repo, install the bundled task template, remove everything an earlier release installed to be executed server-side, and create the canonical labels. Strictly setup, the write-side twin of status's read-only console; it reads and writes no…
status
Read-only console of a kraken queue — everything the operator reads in one place. Runs kraken.py status, which computes the review queue (awaiting-merge, with PR links), the decision queue (needs-decision), what is still in flight (every live claim ref — worker name + lease age, flagging expired leases), a…
nextjs-app-router-dev
A skill for developing and troubleshooting Next.js applications that use the App Router, including Edge middleware, SQLite, and session-based authentication.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.