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/orientationnpx skills add VGrss/Acumen --skill orientationgit 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 | $0.01873 |
| Opus 5 | $0.00029 | $0.00937 |
| Sonnet 5 | $0.00012 | $0.00375 |
| Haiku 4.5 | $0.00006 | $0.00187 |
Grade A, and why
orientation 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 — 135 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
Most products drift. Features accumulate because customers asked, competitors shipped, or someone had a slow week. Over time, the product says it does one thing but actually does twelve — and none of them well enough to be the reason someone chooses it.
Orientation is the audit that catches drift. You are not here to validate. You are here to hold a mirror up and ask: does the product we built match the product we say we are?
Context Pull
Load everything. This is a read-heavy skill:
- Product context. Read
.acumen.md— positioning, thesis, stage, target users, strategy. - Feature inventory. Read
.acumen/features.md— every capability the product has today. - Personas. Read
.acumen/personas.md— who we say we serve, and their behaviors. - Value chain. Read
.acumen/value-chain.md— the end-to-end workflow per persona. Use this to check whether features align with the steps where we claim to bring value. - Competitors. Read
.acumen/competitors.md— how the market frames us vs. alternatives.
If any context file is missing, flag it. Orientation without a feature inventory or personas is guesswork.
Core Protocol
1. Thesis Check
State the product thesis in one sentence. Then ask:
- Can every feature in the inventory be traced back to this thesis?
- Which features serve the thesis directly? Which serve it indirectly? Which don't serve it at all?
- If you removed the orphan features, would anyone notice? Would retention change?
Features that don't connect to the thesis are either: (a) the thesis is wrong and needs updating, or (b) the feature is drift and should be deprecated or spun out.
2. Persona Alignment
For each primary persona in .acumen/personas.md:
- Which features serve this persona's core job?
- Which features are irrelevant to them (clutter)?
- Is there a gap — a job this persona needs done that the product doesn't address?
- Value chain coherence — Do the features we built match the steps we claim to own in
.acumen/value-chain.md? Are there chain steps marked as "Own" with no corresponding feature, or features with no chain step? - Would this persona describe the product the same way the positioning does?
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 · 135 lines · 58 tokens per session scan A 1d742fe6379a
orientation 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 1,873 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
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.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.