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/valuenpx skills add VGrss/Acumen --skill valuegit 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 | $0.00038 | $0.01418 |
| Opus 5 | $0.00019 | $0.00709 |
| Sonnet 5 | $0.00008 | $0.00284 |
| Haiku 4.5 | $0.00004 | $0.00142 |
Grade A, and why
value 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 — 118 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: Value is not what you built — it's the outcome the user got. A feature ships; value is delivered only when the user's situation improves and you can see it in the numbers. If you can't connect a persona to a metric, you don't know if you're delivering value — you're hoping.
Behavior
When called with a specific persona: Build or update the value map for that persona. Focus on what outcome they get, what metric proves it, and whether that metric is actually healthy.
When called without argument: Build the full value map across all personas. Identify where value delivery is proven, assumed, or unmeasured.
Research Process
- Read
.acumen.mdfor product context — north star metric, strategy, business model, success definitions - Read
.acumen/personas.mdfor behavioral personas — job to be done, success criteria, feedback signals - Read
.acumen/features.mdfor feature inventory — what exists, who it serves, what's measured - Read
.acumen/value-chain.mdfor end-to-end workflow — where the product sits, what it owns - Check
.acumen/sources.mdfor data sources — pull real metrics if available - If data sources are configured, pull actual numbers. If not, ask the user to share what they have.
For each persona, answer:
- What value do they get? Not features — outcomes. "Saves 4 hours/week on report generation" not "has a report builder."
- What's the north star metric for this persona? The single number that best captures whether this persona is getting value. This may be the product-wide north star or a persona-specific proxy.
- What are the usage metrics that lead to value? The behavioral signals that predict value delivery — activation events, frequency patterns, depth of engagement, workflow completion rates.
- What's the proof? Current metric values, trends, cohort data. If no data exists, say so — an unmeasured value claim is an assumption.
- What's the value gap? Where is the persona not getting the value they expect? Where does the product promise more than it delivers?
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 · 118 lines · 38 tokens per session scan A c12ca9af07b7
value is a skill published in the GitHub repository VGrss/Acumen (11 stars, last pushed 26d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,418 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.
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…