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/bartolli/kmd/retronpx skills add bartolli/kmd --skill retrogit clone --depth 1 https://github.com/bartolli/kmdWrote 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/bartolli/kmd/retro)<a href="https://agentmods.dev/skills/bartolli/kmd/retro"><img src="https://agentmods.dev/badge/skills/bartolli/kmd/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 | $0.00173 | $0.01736 |
| Opus 5 | $0.00086 | $0.00868 |
| Sonnet 5 | $0.00035 | $0.00347 |
| Haiku 4.5 | $0.00017 | $0.00174 |
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.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retro — Two Questions Before the Primer
Why this exists
A session ends with a primer rewrite so the next cold session starts from truth. The primer author is the same model that did the work — the failure mode is inheriting the session's blind spots straight into the "current truth" document. The retro forces a perspective shift BEFORE authoring: interrogate the session's confidence, convert what surfaces into artifacts, then write the primer from the corrected state.
Verification gates check what you claimed. The retro asks what you did not claim. Precedent: a session's retro surfaced that a just-shipped containment check was looser than its intent and that a fail-closed gate needed to cover a second edge kind — both became story scope extensions, one became a shipped fix. No gate would have caught either, because no claim covered them.
Prerequisites
WIKI_SCOPE: <scope>declared in the project instructions. If missing, suggest/wiki.- An active plan for the scope (dated retro notes land there). Without one, answers route to the primer's Open Questions only.
When it runs
- MANDATORY before authoring or resyncing the primer at a session boundary.
- Worth running at any milestone even mid-session: a release cut, a fix batch drained, a plan phase flip.
The protocol
Step 1 — Answer the two questions
In order, in the visible response:
- What are you least confident about right now?
- What's the biggest thing we're missing about the situation right now? What don't I realize?
Answering rules:
- Answers are about the WORK, not the worker. Name code, artifacts, and measurements — never feelings, apologies, or process narrative.
- Every answer carries a location (file, story, number) and a falsification path: what a future session runs or reads to confirm or kill the concern.
- Question 2 demands the perspective shift: re-read the session's own claims as a skeptic. What blind spot did every gate share? What would an adversarial reviewer probe first? What state does the session assume persists that nothing actually verifies?
- Banned: performative humility ("mistakes may have been made"), vacuous confidence ("everything is verified"), and re-announcing already-filed open stories as discoveries — reference them instead.
- "Nothing" is not an acceptable answer to either question. There is always a least-confident item; if all concerns feel small, rank them and name the top one.
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 · 156 lines · 173 tokens per session scan A 18fa30013856
retro is a skill published in the GitHub repository bartolli/kmd (7 stars, last pushed 23d ago), licensed MIT. It adds 173 tokens to every session and 1,736 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…