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 commands/vimalk0703/shipworthy/retrogit clone --depth 1 https://github.com/Vimalk0703/shipworthyWrote 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/vimalk0703/shipworthy/retro)<a href="https://agentmods.dev/commands/vimalk0703/shipworthy/retro"><img src="https://agentmods.dev/badge/commands/vimalk0703/shipworthy/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 | $0.00000 | $0.00342 |
| Opus 5 | $0.00000 | $0.00171 |
| Sonnet 5 | $0.00000 | $0.00068 |
| Haiku 4.5 | $0.00000 | $0.00034 |
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 3d 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
Before executing this command, output:
⚓ shipworthy › command:
/retro— extracting session learnings
Run a retrospective on the current session.
Analyze this entire conversation and extract what can be learned to make the next session better.
Process
Invoke the retrospective skill and follow its full process:
-
Extract signals from this conversation:
- Corrections the user made ("no", "not that", "I meant...")
- Work that was redone or changed approach mid-stream
- Steps that were improvised (not in any plan or skill)
- Things that worked perfectly on first try
- Which Shipworthy skills fired and helped
- Which situations had no relevant skill (skill gaps)
- User preferences discovered through their feedback
-
Map each signal to the relevant Shipworthy skill (or note the gap)
-
Present a findings table for the user to review:
- Each finding with type, description, proposed action
- User approves/rejects each item
-
Apply approved changes:
- Save project learnings to
.shipworthy/learnings/ - Propose (but don't auto-apply) skill file updates
- Suggest auto-memory entries for user-level preferences
- Save project learnings to
-
Update the session summary with retrospective results
Important
- Only analyze what already happened — don't suggest new work
- Be specific: "User corrected database choice from SQLite to PostgreSQL" not "There were some database discussions"
- If nothing notable happened (quick fix session), say so: "Clean session, no learnings to capture"
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.
- 3d ago First seen · 41 lines · 0 tokens per session scan A d52f974de003
retro is a command published in the GitHub repository Vimalk0703/shipworthy (7 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 342 tokens. 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 commands, from other repositories
cmd
Alpha pack command fixture.
dare-blueprint
Gera somente DARE/BLUEPRINT.md a partir do DARE/DESIGN.md.
dare-bugfix-design
Diagnostica bug em projeto existente e planeja correção cirúrgica via Método DARE. Gera DARE/DESIGN-Bugfix-[Nome].md com causa raiz, riscos de regressão e plano de ação mínimo.
status
Report the current state of the SpecRoute skeleton - which top-level dirs exist, which artifacts have been drafted, what's outstanding.
verify-sources
Verify all source URLs in TIPS.md are still reachable.
scan-x
Manually scan X for new Boris Cherny posts since last scan.