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 agentmods add skills/cookys/autopilot/retronpx skills add cookys/autopilot --skill retrogit clone --depth 1 https://github.com/cookys/autopilotWrote 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/cookys/autopilot/retro)<a href="https://agentmods.dev/skills/cookys/autopilot/retro"><img src="https://agentmods.dev/badge/skills/cookys/autopilot/retro.svg" alt="Measured on agentmods" 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 | $0.00125 | $0.01646 |
| Opus 5 | $0.00063 | $0.00823 |
| Sonnet 5 | $0.00025 | $0.00329 |
| Haiku 4.5 | $0.00013 | $0.00165 |
Grade A, and why
retro 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 4d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
retro — Engineering Retrospective
Arguments
| Invocation | Window |
|---|---|
/retro |
Last 7 days (default) |
/retro 14d |
Last 14 days |
/retro 30d |
Last 30 days |
Parse the argument: extract the number before d. Default to 7 if no argument.
Step 1: Data Collection (run in parallel)
Run all six collection commands simultaneously using parallel Bash calls. Set DAYS to the parsed window size.
Run the six collection commands — 1a commits+stats, 1b per-commit file breakdown, 1c timestamps for session detection, 1d file hotspots, 1e project-completion delta, 1f review-loop lens (scripts/retro-review-loop.js --days DAYS --json — the hetero-dispatch/review/debate effort git history can't see) — from references/data-collection.md, substituting DAYS.
1g Escalation-ledger scan (quality-floor L4): for each project dir in docs/projects/ and docs/projects/_archive/ with a tree/events.jsonl touched in the retro window, run node scripts/tree.js escalations <proj> and aggregate escalation_opened events by stage/why_not_mechanical; report counts + recurring themes. Recurring (≥2 similar) entries are DEMOTION CANDIDATES — hand them to skills/distill's demotion-drafting step.
Step 2: Compute Metrics
From the collected data, calculate:
Core Metrics
- Total commits — count of commits in window
- Insertions / Deletions / Net LOC — sum from shortstat
- Commit days — distinct dates with commits
- Shipping streak — longest run of consecutive days with commits
Test Ratio
- Test LOC — insertions in files matching
test/or_testorTest.cpp - Test ratio — test LOC / total LOC (target: >15%)
Commit Type Breakdown
Parse commit message prefixes (case-insensitive):
feat/add→ Featurefix→ Bugfixrefactor/clean→ Refactortest→ Testdoc/docs→ Documentationchore/build/ci→ Chorerefine/improve→ Refinement- Everything else → Other
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 158 lines · 125 tokens per session scan A 2ca500ba99f5
retro is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed today), licensed MIT. It adds 125 tokens to every session and 1,646 once invoked, about $0.0006 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
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
sap-transport-overview
System-wide inventory of open transport requests — every visible modifiable request, who owns it, how big it is, and supported risk signals such as empty/local requests, explicit locks, and confirmed manifest overlaps. Headers-only and cheap; NO source diffs. Use when asked "what transports are open in the system"…
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.
finn-spec
Interview the user about a raw idea until confident, then file a build-ready issue in Linear. Use when asked to run Finn-loop's spec interview, draft a queue-ready issue, or plan a feature. Interactive — requires the user present; never run unattended.