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/featuresnpx skills add VGrss/Acumen --skill featuresgit clone --depth 1 https://github.com/VGrss/AcumenWhat 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 | $0.00025 | $0.00773 |
| Opus 5 | $0.00013 | $0.00387 |
| Sonnet 5 | $0.00005 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
features 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 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.
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 — 86 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: Know what you've built before deciding what to build next. Features without owners decay. Features without metrics are assumptions.
Behavior
When called with a specific feature or area: Add or update that entry. Ask the user about its current status, who it serves, and how they know it's working.
When called without argument: Scan the codebase and refresh the full inventory. Cross-reference with personas from .acumen/personas.md if available.
Research Process
- Read
.acumen.mdfor product context — strategy, metrics, constraints - Read
.acumen/features.mdfor existing inventory - Read
.acumen/personas.mdfor persona alignment (if exists) - Scan the codebase:
- Route handlers and pages — each is likely a feature surface
- API endpoints — capabilities exposed
- Database models — entities the product manages
- Navigation and menus — user-facing feature organization
- Feature flags or config — features in rollout or gated
- For each feature, determine:
- Which persona it serves (or if it's orphaned)
- Current status (shipping, beta, deprecated, broken, unused)
- Key metric (how you know it's delivering value — or that no one is measuring)
- Owner (who's responsible — or if no one is)
Output
Write to .acumen/features.md:
# Feature Inventory
_Last updated: [date]_
## Feature Map
| Feature | Serves Persona | Status | Key Metric | Owner | Notes |
|---------|---------------|--------|------------|-------|-------|
| [name] | [persona] | [shipping/beta/deprecated/unknown] | [metric or "unmeasured"] | [owner or "unowned"] | [notes] |
## Feature Areas
Group features into coherent areas. For each area:
### [Area Name]
- **Purpose**: [Why this area exists]
- **Features**: [List of features in this area]
- **Health**: [Overall assessment — thriving, stable, neglected, bloated]
## Gaps
[Features that personas need but don't exist yet. Features that strategy calls for but haven't been built. Reference personas and strategy from .acumen.md.]
## Decay Watch
[Features showing signs of neglect: unowned, unmeasured, no recent commits, known bugs unfixed. These aren't necessarily bad — but they need a conscious decision: invest, maintain, or kill.]
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 · 86 lines · 25 tokens per session scan A d0b5deccb27a
features is a skill published in the GitHub repository VGrss/Acumen (11 stars, last pushed 26d ago), licensed Apache-2.0. It adds 25 tokens to every session and 773 once invoked, about $0.0001 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…