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/incrementnpx skills add VGrss/Acumen --skill incrementgit 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 | $0.00058 | $0.03213 |
| Opus 5 | $0.00029 | $0.01606 |
| Sonnet 5 | $0.00012 | $0.00643 |
| Haiku 4.5 | $0.00006 | $0.00321 |
Grade A, and why
increment 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 — 255 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.
- Diverge first — always. An increment never scopes a path that hasn't been diverged. If a
/workshopreport already exists for this problem and a path was chosen, read it and proceed. If not, run/workshopnow, produce the report, and converge on a single path before writing a line of the increment. The explored options live in the workshop report; the increment scopes only the chosen path and does not re-litigate the alternatives. Scale the divergence to the size — a Small fix gets a quick fork exploration, not a full workshop — but it happens.
Mindset
An increment is a commitment to ship a complete user outcome. Not a feature request. Not a brainstorm. Not a backlog item with aspirations. It is the document that says: "This is what we are building, why, for whom, and how we know it worked." If you cannot fill every section with specific, grounded information, the increment is not ready to build.
This skill scopes one path — the shape that won its /workshop divergence. The alternatives were explored in the workshop report and deliberately set aside; the increment commits to a single shape and doesn't re-open the fork. If the path isn't chosen yet, you're not ready to scope — go diverge first. Don't scope two increments in parallel.
A spec is a thinking tool, not a documentation exercise. The competitive context should shape the scope. The persona reactions should challenge the solution. The user signal should validate the problem. If these inputs don't change what you write, you are not using them.
Scope by outcome, not by time. "What can we build in two weeks?" produces mediocre features. "What is the minimum that changes user behavior?" produces focused ones. Cut features, not corners.
Length discipline
A reader should absorb the whole increment in a few minutes. Terseness is a feature, not a compromise.
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 · 255 lines · 58 tokens per session scan A ac97706ef871
increment is a skill published in the GitHub repository VGrss/Acumen (11 stars, last pushed 26d ago), licensed Apache-2.0. It adds 58 tokens to every session and 3,213 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.
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…
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.