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/vgrss/acumen/narratenpx skills add VGrss/Acumen --skill narrategit clone --depth 1 https://github.com/VGrss/AcumenWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vgrss/acumen/narrate)<a href="https://agentmods.dev/skills/vgrss/acumen/narrate"><img src="https://agentmods.dev/badge/skills/vgrss/acumen/narrate.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00037 | $0.01368 |
| Opus 5 | $0.00018 | $0.00684 |
| Sonnet 5 | $0.00007 | $0.00274 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
narrate 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 4d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Narrate
Preparation
Before anything else, invoke /product-thinking to load strategic context, user segments, and current product landscape. Communication without context is just words arranged nicely.
Mindset
Write for the audience, not for the record. An exec summary is not a PRD with details removed. An engineering brief is not a strategy deck with code references added. Each audience has a different decision to make, a different vocabulary, and a different tolerance for detail.
And when stakeholders disagree, map incentives, not positions. What someone says they want and what they actually optimize for are often different things.
Core Reflex
Identify the audience and the decision they need to make. Strip everything that doesn't serve that decision. Then change three things:
- Vocabulary — match the audience's language. Execs think in bets and returns. Engineers think in constraints and tradeoffs. Customers think in outcomes. Investors think in markets and moats.
- Altitude — execs want the 30,000-foot view with one zoom-in on the riskiest part. Engineers want ground-level specifics with one zoom-out on why it matters. Customers want eye-level: what changed, what they can do.
- Structure — lead with what the audience cares about most. For execs, the decision. For engineers, the scope. For customers, the benefit. For investors, the opportunity.
Five Formats
1. Executive (1 page max)
Structure: The bet, why now, expected outcome, what you need from them.
Lead with the decision, not the context. They have 5 minutes and 12 other things competing for attention. If the first paragraph doesn't tell them what you want and why it matters, they'll skim the rest — and you'll get a non-answer.
- The bet: one sentence on what you're proposing and the expected return
- Why now: what changed that makes this urgent — market shift, competitive move, data inflection
- Expected outcome: specific metrics with timelines, not vague improvement
- The ask: what you need — budget, headcount, prioritization call, sign-off
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.
- 4d ago First seen · 108 lines · 37 tokens per session scan A 4619829cd756
narrate is a skill published in the GitHub repository VGrss/Acumen (11 stars, last pushed 29d ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,368 once invoked, about $0.0002 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…