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/tslateman/duet/retronpx skills add tslateman/duet --skill retrogit clone --depth 1 https://github.com/tslateman/duetWrote 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/tslateman/duet/retro)<a href="https://agentmods.dev/skills/tslateman/duet/retro"><img src="https://agentmods.dev/badge/skills/tslateman/duet/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 | $0.00017 | $0.00420 |
| Opus 5 | $0.00009 | $0.00210 |
| Sonnet 5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
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.
What it actually says
Session Retrospective
Overview
Reflect on the work just completed in this conversation. Extract insights, not summaries.
What I Learned
Identify 2-4 concrete technical insights from this session:
- Patterns discovered or reinforced
- Gotchas or surprises encountered
- Techniques that worked well (or didn't)
- Connections to other parts of the codebase
Focus on insights, not a summary of actions taken.
What to Think About Next
Surface 2-4 open threads worth considering:
- Unfinished work or TODOs
- Edge cases or risks not yet addressed
- Potential improvements or refactors
- Questions that came up but weren't resolved
Be specific—name files, functions, or concepts rather than speaking abstractly.
Memory Health Check
Before asking about persistence, check the current project's MEMORY.md:
- Read the file from the project's auto memory directory
- Count lines -- if over 50, note the size
- Scan for staleness signals:
- Items containing "resolved", "fixed", "done", "completed"
- Date references from more than 30 days ago
- Sections that duplicate CLAUDE.md headers
- Report briefly: "MEMORY.md: [N] lines, [issues found or 'healthy']"
If issues are found, include them in the question to the user -- e.g., "MEMORY.md has 3 stale items. Want to prune them while persisting new insights?"
After generating the retro, ask the user if any insights are worth persisting to auto memory. Use AskUserQuestion with options like "Yes, update MEMORY.md", "Yes, and prune stale items", and "No, just this session".
If yes, read the current MEMORY.md from the project's auto memory directory and intelligently merge the new insights—don't duplicate existing points, add new ones under the appropriate sections.
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 · 53 lines · 17 tokens per session scan A c9632fc42426
retro is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 7d ago), licensed MIT. It adds 17 tokens to every session and 420 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 2026-08-31.
Other skills, from other repositories
roadmap-to-workflow
Fan an approved .task/roadmap/ .md out to a dynamic Workflow — parallel planning, serialized implementation, dependency-ordered waves.
to-plan
Capture the chat into .task/task/ .md with ## Description plus ## Plan (Goal/Touches/Logic) — the deepest one-task capture.
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
to-roadmap
Capture a multi-task initiative into .task/roadmap/ .md — a phase-grouped backlog of ready-to-pick-up items.
to-task
Capture the chat (or a roadmap item) into .task/task/ .md — ## Description only, no ## Plan.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.