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/nmrtn/nanopm/pm-solutionsnpx skills add nmrtn/nanopm --skill pm-solutionsgit clone --depth 1 https://github.com/nmrtn/nanopmWhat 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 | $0.00119 | $0.06460 |
| Opus 5 | $0.00060 | $0.03230 |
| Sonnet 5 | $0.00024 | $0.01292 |
| Haiku 4.5 | $0.00012 | $0.00646 |
Grade C, and why
pm-solutions scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
{ echo "ERROR: nanopm not installed. Run: curl -fsSL https://raw.githubusercontent.com/nmrtn/nanopm/main/setup | bash"; exit 1; } Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
{ echo "ERROR: nanopm not installed. Run: curl -fsSL https://raw.githubusercontent.com/nmrtn/nanopm/main/setup | bash"; exit 1; } How it starts
The opening of the file, as written. The whole thing — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-host portability rules. When invoking
AskUserQuestion:
- The
headerfield MUST be a short noun phrase (≤ 12 characters). Mistral Vibe rejects longer headers withstring_too_long. Pick from:Start,Target,Scope,Audience,Methodology,Feature,Question,Confirm,Choose.- The
optionslist MUST have at least 2 items. Vibe rejects empty/single-option calls. For free-text input, always provide ≥ 2 framing options (e.g.Yes, here's the input/Skip) — never callask_user_questionwithoptions: [].
Preamble (run first)
source ~/.nanopm/lib/nanopm.sh 2>/dev/null || \
source .nanopm/lib/nanopm.sh 2>/dev/null || \
{ echo "ERROR: nanopm not installed. Run: curl -fsSL https://raw.githubusercontent.com/nmrtn/nanopm/main/setup | bash"; exit 1; }
nanopm_preamble
_OPP_DIR=".nanopm/wiki/entities/opportunities"
_SOL_DIR=".nanopm/wiki/entities/solutions"
mkdir -p "$_SOL_DIR"
What this skill does
/pm-solutions <opportunity-slug> is the Solutions node of the Opportunity Solution Tree
(Outcome → Opportunity → Solution → Assumption). nanopm already produces Outcomes (objectives)
and Opportunities (the DB), but nothing bridged an opportunity to a compared set of candidate
solutions — so the founder picked the first idea in his head and jumped straight to /pm-prd. This
skill fills that gap: it convenes a panel of three fixed expert lenses (Eng / Design / Business),
makes them propose competing solutions in parallel, then converges them into a comparison the
founder can weigh.
The shape is the same recipe each run, built on the three wiki primitives — query → reasoning →
ingest (no bespoke read logic), with lint keeping it honest after the fact:
- RESOLVE — resolve the opportunity slug to one file (or list candidates and stop).
- QUERY (read primitive) — one
nanopm_query_promptsubagent reads the wiki and returns a cited, lens-relevant grounding for the panel (the persona's JTBD, the objectives / strategy / bet, the product surface + structural constraints) — the same query op every other skill uses, instead of leaning on the preamble briefs alone. - DIVERGE (reasoning primitive) — three lens-subagents (Eng / Design / Business) dispatched concurrently in one turn, each grounded in the opportunity file + the cited QUERY digest.
- CONVERGE — one pass that dedups overlapping proposals and emits ≥3 solutions, each with the full field set; the converged comparison table is canonical, but every row keeps its lens tag and a one-line dissent note — the room stays visible.
- WRITE — one
wiki/entities/solutions/<slug>.mdper solution via the ingestapplyprimitive, regenerateINDEX.md, append a bidirectional pointer block to the parent opportunity page. - CHOOSE — present the comparison; the founder shortlists, then marks one
chosen. The agent never auto-chooses.
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 · 443 lines · 119 tokens per session scan C d9073a9e8edc
pm-solutions is a skill published in the GitHub repository nmrtn/nanopm (48 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 6,460 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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…