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/scoutnpx skills add VGrss/Acumen --skill scoutgit 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/scout)<a href="https://agentmods.dev/skills/vgrss/acumen/scout"><img src="https://agentmods.dev/badge/skills/vgrss/acumen/scout.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 | $0.00044 | $0.01518 |
| Opus 5 | $0.00022 | $0.00759 |
| Sonnet 5 | $0.00009 | $0.00304 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
scout 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY PREPARATION
Invoke /product-thinking — it contains product principles and the Context Gathering Protocol. Follow the protocol before proceeding — if no product context exists yet, you MUST run /teach-acumen first.
Mindset: Competitors are everyone hired for the same job — not just companies with similar feature lists. A spreadsheet is a competitor. Doing nothing is a competitor. The intern who does it manually is a competitor.
Competition is about who else gets hired for the job, not who has more checkmarks on a feature matrix. Users don't compare products in a vacuum — they compare the pain of switching against the pain of staying.
Behavior
When called with a specific competitor or market area: Research and add/update that entry in the map. Ask the user what they know, what prompted the scout, and what they're worried about.
When called without argument: Review the full map for staleness and gaps. Flag competitors that haven't been updated recently. Identify missing entrants.
When called with "deep [competitor]" or for strategic decisions: Switch to deep analysis mode (see below).
Research Process (Standard Mode)
- Read
.acumen.mdfor product context — users, job to be done, strategy, deliberate exclusions - Read
.acumen/competitors.mdfor existing map - For each competitor (new or updated), gather:
- Their website URL
- Their category: Direct (same job, same approach), Indirect (same job, different approach), or Adjacent (different job, overlapping users)
- What job they're hired for (may overlap partially with yours)
- How they position themselves
- Their actual strengths (not what they claim — what users would say)
- Their real weaknesses (not surface-level — structural ones)
- Their moat (network effects, data, switching costs, brand, distribution)
- Recent moves (launches, pivots, pricing changes, acquisitions)
- Assess feature parity traps — features competitors have that you might reflexively copy but shouldn't
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 · 155 lines · 44 tokens per session scan A 55bf47b7ef53
scout is a skill published in the GitHub repository VGrss/Acumen (11 stars, last pushed 28d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,518 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…