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/workshopnpx skills add VGrss/Acumen --skill workshopgit 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 | $0.00056 | $0.02105 |
| Opus 5 | $0.00028 | $0.01052 |
| Sonnet 5 | $0.00011 | $0.00421 |
| Haiku 4.5 | $0.00006 | $0.00211 |
Grade A, and why
workshop 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY PREPARATION
Invoke /product-thinking — it contains the Context Gathering Protocol and the AI Slop Test. Follow the protocol before proceeding.
Mindset
A workshop is divergence. Its one job: take a single problem or opportunity and expose the full range of shapes a solution could take — so the choice of shape is deliberate, not the first plausible idea.
The two failure modes:
- First-idea lock-in. The team names a problem, pictures one solution, and scopes it. The workshop's job is to prove there were nine other shapes worth seeing first.
- Ten variations of one idea. Producing "10 options" that all feel like the same product to a user is not divergence — it's padding. If two options would feel identical in the user's hands, they count as one.
This is not brainstorming. Brainstorming produces 40 ideas and zero decisions. A workshop produces genuinely different options and a recommended direction. Push back on weak options. Kill duplicates. The output is a clear map of the solution space plus a pointer to where to go next.
Input
A workshop needs one problem or opportunity to diverge on. It comes from:
/diagnose— a problem or opportunity it surfaced (the common path). Read the referenced report in.acumen/reports/..acumen/value-chain.md— an opportunity listed against an extension point in the value chain.- Directly stated — the user hands you a problem in the argument.
If the input is vague ("engagement is low"), sharpen it to a one-line problem statement before diverging — a fuzzy problem produces fuzzy options. If you cannot sharpen it from context, run /diagnose first and say so.
Context Pull
Load context as fuel for divergence, not to discover the problem (that was /diagnose's job):
- Product context. Read
.acumen.md— thesis, positioning, stage, constraints. Options that dilute the thesis still belong on the board; flag them, don't hide them. - Personas. Read
.acumen/personas.md— whose problem this is, their workarounds, their daily workflow. - Features. Read
.acumen/features.md— what exists today that an option could repurpose, extend, or replace. - Value chain. Read
.acumen/value-chain.md— where in the workflow the problem sits and which adjacent steps an option could reach into. - Competitors. Read
.acumen/competitors.md— how others solve this shape of problem, and where the white space is.
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 · 171 lines · 56 tokens per session scan A 4933b953f4f9
workshop is a skill published in the GitHub repository VGrss/Acumen (11 stars, last pushed 26d ago), licensed Apache-2.0. It adds 56 tokens to every session and 2,105 once invoked, about $0.0003 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…