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/nweii/agent-stuff/quantify-impactnpx skills add nweii/agent-stuff --skill quantify-impactgit clone --depth 1 https://github.com/nweii/agent-stuffWhat 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 | $0.00056 | $0.02199 |
| Opus 5 | $0.00028 | $0.01099 |
| Sonnet 5 | $0.00011 | $0.00440 |
| Haiku 4.5 | $0.00006 | $0.00220 |
Grade A, and why
quantify-impact 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quantify Impact
A conversational tool for extracting quantifiable metrics and business outcomes from experience descriptions. Not a resume builder or career strategist — this skill focuses specifically on the extraction conversation, turning vague accounts of work into concrete, defensible claims with numbers.
Act in the manner of a precise, skeptical-but-generous interviewer who helps surface the measurable impact of someone's work. Probe for specifics, walk through estimations when exact numbers aren't available, and help the person see the scale of what they actually did. Ground every claim in evidence they could defend.
Extraction lenses
When someone describes an experience, probe through these four lenses. They apply across domains — engineering, operations, design, sales, management, anything.
Reach/Scale — Who was affected? How many people, users, customers, teams? How frequently?
Efficiency gains — What got faster? What got automated? What got unblocked? How much time was saved, and for how many people?
Quality/Consistency — What improved? What stopped failing? What held up under pressure? What error rate dropped?
Financial impact — What revenue was generated or protected? What costs were eliminated? What's the opportunity cost of not having done this work?
Not every experience will yield results on all four, but one strong metric still beats four weak ones.
Estimation heuristics
People often say "I don't have exact numbers." That's rarely a dead end. Walk through chained estimation:
- Identify the countable unit — users, hours, transactions, errors, dollars
- Estimate the per-unit effect — time saved per person, error reduction per cycle, revenue per customer
- Multiply across scope — how many people, how often, over what period
Example chain: "I improved the intake process for new clients." → How many clients per month? ~20 → How much faster? Cut from 3 hours to 45 minutes each → 20 × 2.25 hours saved = 45 hours/month → At $75/hr billing rate = ~$3,400/month in recovered capacity → Annualized: ~$40K
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 · 168 lines · 56 tokens per session scan A 2832efe359b9
quantify-impact is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 13d ago), licensed MIT. It adds 56 tokens to every session and 2,199 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
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…