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/matthewdigiuseppe/mstack/retronpx skills add matthewdigiuseppe/MStack --skill retrogit clone --depth 1 https://github.com/matthewdigiuseppe/MStackWhat 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 | $0.00057 | $0.00676 |
| Opus 5 | $0.00028 | $0.00338 |
| Sonnet 5 | $0.00011 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00068 |
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mstack:retro
Stage: reflect Voice: coach
When to invoke
After acceptance, after rejection, after a major R&R. Memory is freshest now; in a month it's gone.
Procedure
-
Load.
.mstack/config.yaml(status, target journals), the chronological set of.mstack/*.mdfiles, git log of the project if available, decision letters insubmission/. -
Reconstruct the timeline.
- First commit /
mstack-initdate. - Major milestones (lit-map, prereg, first analysis, first draft, submission, R1, R2, accept).
- Approximate days between milestones.
- First commit /
-
Five questions — answer each in one paragraph. Push for specifics; vague retros are worth nothing.
- Where did time actually go? Not where you expected — where it actually went. Compare estimated vs. actual on the longest stage.
- What was the biggest unforced error? Something you did that cost time / quality and that you knew, at the time, you shouldn't be doing.
- What surprised you? A finding, a referee comment, a methodological issue, a writing block — something that wasn't on your map at the start.
- What worked? A practice / habit / decision worth keeping. The retro is also for capturing wins.
- What's the one systematizable lesson? A rule for next time. Concrete enough to operationalize as a skill, a checklist, or a global-memory entry.
-
Save to
.mstack/retro.md. -
Promote. If question 5 produced a lesson worth carrying across papers, suggest the user run
/mstack:learnto write it to their global memory (not just.mstack/learnings.jsonl, which is paper-local).
Outputs
.mstack/retro.md.- Summary block: timeline summary + the one systematizable lesson + suggested follow-up.
Anti-patterns to refuse
- Generic lessons. "Communicate more with coauthors" is not a lesson; "set a 30-min check-in every Friday with C" is.
- Skipping the timeline. Without the timeline, the retro is vibes.
- Skipping the wins. A retro that only catalogs failures hides what to keep.
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 · 56 lines · 57 tokens per session scan A 1cc0965a3565
retro is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 6d ago), licensed MIT. It adds 57 tokens to every session and 676 once invoked, about $0.0003 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
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…