Borrowing it
Nothing to install: this file belongs to VGrss/Acumen. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/VGrss/Acumen/main/.agents/skills/teach-acumen/SKILL.mdgit 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/teach-acumen)<a href="https://agentmods.dev/skills/vgrss/acumen/teach-acumen"><img src="https://agentmods.dev/badge/skills/vgrss/acumen/teach-acumen/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vgrss/acumen/teach-acumen"><img src="https://agentmods.dev/badge/skills/vgrss/acumen/teach-acumen.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00031 | $0.01795 |
| Opus 5.5 | $0.00012 | $0.00718 |
| Sonnet 5.5 | $0.00006 | $0.00359 |
| Haiku 4.5 | $0.00003 | $0.00179 |
Grade A, and why
teach-acumen 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 2mo 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gather product context for this project, then persist it for all future sessions.
Step 1: Explore the Codebase
Before asking questions, thoroughly scan the project to discover what you can:
- README and docs: Project purpose, target audience, stated goals
- Database schema: Models, relationships, what data matters
- API routes and actions: What the product actually does, core workflows
- Analytics / tracking: What's measured today, event names, funnels
- Existing specs or PRDs: Past decisions, constraints, product language
- Package.json / config: Dependencies that hint at product capabilities (payments, auth, notifications, etc.)
Note what you've learned and what remains unclear.
Step 2: Ask Product-Focused Questions
Ask the user directly. Focus only on what you couldn't infer from the codebase:
Users & Market
- Who uses this? What job are they hiring it to do?
- Who else gets hired for the same job? (Direct competitors, spreadsheets, manual processes, doing nothing)
- What's the switching cost away from you?
Value Chain
- What does the user do before and after using the product? Walk me through the full workflow end-to-end.
- Where in that workflow does the product bring value? Where is the user on their own (manual steps, other tools)?
- Are there different workflows per user type?
Business Model
- How does it make money? (Or how will it?)
- What stage is the product in? (Pre-launch, finding PMF, scaling, mature)
- Top 3 goals for the next quarter
Strategy
- What's the opinionated bet this product makes? (The thing competitors won't or can't do)
- What are you deliberately NOT building?
- Biggest risk to the product right now
Metrics
- What's measured today? What should be?
- North star metric (the single number that best captures value delivered)
- How do you define success for a feature?
Feedback Source
- Where does user feedback live? (Linear, Notion, Slack channel, local file, interviews, support tickets, other)
- How often is it reviewed?
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.
- 2mo ago First seen · 195 lines · 31 tokens per session scan A 94aba4871b8d
teach-acumen is a skill published in the GitHub repository VGrss/Acumen (12 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,795 once invoked, about $0.0001 per session on Opus 5.5. 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.
teach-acumen compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| teach-acumenVGrss/Acumen | Skill | 12 | 3mo ago | Apache-2.0 | A | 31 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |