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/romerma/mstack/designnpx skills add romerma/mstack --skill designgit clone --depth 1 https://github.com/romerma/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 | $0.00628 |
| Opus 5 | $0.00028 | $0.00314 |
| Sonnet 5 | $0.00011 | $0.00126 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
design 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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design
1. Ground
/mstack:understand the subsystems this touches. Designing against a guess about the current
shape produces a design that fits a system nobody has.
2. Fix the criteria before you see the candidates
Three to six concrete criteria for this specific problem. Write them down now, and do not show them to the candidate generators. Criteria invented after the fact select for whichever candidate you already liked.
3. Design it twice
At least two structurally distinct candidates, not two flavours of the same shape. If the constraints genuinely forced one answer, say so and name the constraint: "this was the only viable shape because X" is a legitimate outcome, and it is different from not having looked.
Fan them out in one message so they cannot see each other. Each writes to its own path. If they diverge wildly, the framing was underspecified: reframe and rerun rather than averaging the divergence.
4. Judge, then graft
One judge, on a different model from the generators, scoring against the criteria from step 2. Pick a base, graft what is better from the others, and say what you rejected and why.
5. Write it down
.mstack/specs/<slug>/design.md, or a decision row if there is no spec:
- Problem. What makes the shape non-obvious. One paragraph.
- Usage. The caller's view, written first. The type sketch derives from this, and when the two disagree you reconcile the sketch to the usage. The caller's experience is the spec; the types serve it.
- Shape. Data structures, then how data moves through the signatures.
- Rejected alternatives. Required. A design with no rejected alternative is a first idea.
- Trade-offs accepted. In the form "we accept X in exchange for Y."
- Open questions. Phrased as questions. Only genuinely deferrable ones: if the answer would change the shape, resolve it now.
Red flags
- Shallow module. The interface costs as much to learn as the implementation it hides.
- Information leakage. The same design decision appears in two places.
- Temporal decomposition. Modules split by execution order rather than by what they hide.
- Pass-through method. A method that does nothing but call another with the same signature.
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.
- yesterday First seen · 58 lines · 57 tokens per session scan A 81de9e9caffa
design is a skill published in the GitHub repository romerma/mstack (1 stars, last pushed 8d ago), licensed MIT. It adds 57 tokens to every session and 628 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 2026-08-31.
Other skills, from other repositories
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
spec-kitty-spdd-reasons
Drive REASONS Canvas authoring and review for Spec Kitty missions that opted in to Structured-Prompt-Driven Development (SPDD) via charter selection. Triggers: "use SPDD", "use REASONS", "generate a REASONS canvas", "apply structured prompt driven development", "make this mission SPDD". Does NOT handle: enforcing SPDD…
dependency-upgrade
Plan, batch, and verify dependency upgrades safely. Triages outdated packages into risk tiers, upgrades in order (dev/minor/patch first, runtime majors last), verifies each batch, and produces an auditable commit sequence. Use when asked to "upgrade deps", "bump packages", "update nodemodules", "fix vulnerabilities"…
forensics
Post-mortem a failed GSD auto-mode run. Traces symptom to root cause via .gsd/ activity, journal, metrics, and lock artifacts, producing a filing-ready bug report with file:line refs and a fix suggestion. Use when asked to "forensics", "post-mortem", "why did auto-mode fail", "trace the stuck loop", "debug the crash"…