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/learnnpx skills add matthewdigiuseppe/MStack --skill learngit 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 | $0.00052 | $0.00509 |
| Opus 5 | $0.00026 | $0.00254 |
| Sonnet 5 | $0.00010 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
learn 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 2d 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
/mstack:learn
Stage: power Voice: memory
When to invoke
Whenever you find yourself telling Claude the same paper-specific fact twice. The convention belongs in the paper's memory, not in your head.
Argument
$ARGUMENTS — the fact to remember. Free-form text; this skill will normalize it.
Procedure
-
Classify the fact into one of:
variable_name— naming convention for a key variable.convention— analytical / coding convention specific to this paper.decision— a design or framing decision (with rationale).preference— output / formatting / style preference.reference— pointer to an external resource specific to this paper.other— free-form.
-
Normalize. Strip whitespace; trim trailing punctuation; capitalize the sentence.
-
Append a JSON line to
.mstack/learnings.jsonl:{"date":"YYYY-MM-DD","kind":"<class>","fact":"<normalized fact>"} -
Echo back what was written so the user can confirm.
-
Hint at scope. If the fact looks like it generalizes across papers (a methodological habit, a tooling preference, a writing rule), tell the user to consider also adding it to their global memory (
~/.claude/CLAUDE.md) rather than only here.
Outputs
.mstack/learnings.jsonl— one new line.- Summary: the new line + scope hint if applicable.
Anti-patterns to refuse
- Storing transient state. "Currently working on table 3" is conversation context, not memory. Don't write it.
- Storing what's already in code. If the convention is encoded in a script, the script is the memory.
When to call other skills
- If the fact crosses papers, suggest writing to global memory rather than just here.
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.
- 2d ago First seen · 60 lines · 52 tokens per session scan A 60dd71529763
learn is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 6d ago), licensed MIT. It adds 52 tokens to every session and 509 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…