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/defensibilitynpx skills add VGrss/Acumen --skill defensibilitygit clone --depth 1 https://github.com/VGrss/AcumenWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vgrss/acumen/defensibility)<a href="https://agentmods.dev/skills/vgrss/acumen/defensibility"><img src="https://agentmods.dev/badge/skills/vgrss/acumen/defensibility.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00043 | $0.03444 |
| Opus 5 | $0.00022 | $0.01722 |
| Sonnet 5 | $0.00009 | $0.00689 |
| Haiku 4.5 | $0.00004 | $0.00344 |
Grade A, and why
defensibility 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 4d 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 — 309 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
Features can be copied in a quarter. Moats take years to build — if they can be built at all. Defensibility is the audit that tells you where your product is genuinely hard to replicate, where it's vulnerable, and where to concentrate effort to widen the gap.
Most products have less defensibility than their founders think. Brand is not a moat unless switching costs are high. "First mover" is not a moat unless you've converted the head start into something structural. Be honest. The point is not to feel good — it's to know where to build.
In the AI era, a new class of threats has emerged: agents that can automate workflows, commoditize integrations, and make context portable. This audit evaluates both classical moats and AI-era resilience.
Context Pull
- Product context. Read
.acumen.md— strategy, stage, positioning. - Competitors. Read
.acumen/competitors.md— what competitors have, their moats, recent moves. - Features. Read
.acumen/features.md— current capabilities and their maturity. - Personas. Read
.acumen/personas.md— who depends on us and why they'd stay or leave. - Value chain. Read
.acumen/value-chain.md— where the product sits in each persona's workflow. Use this directly for Section 4 (Value Chain Analysis) and Section 5 (Switching Cost Anatomy).
Framing
Before analysis, establish scope. If the user hasn't specified, ask — one question at a time:
Q1 — Object of analysis:
"What exactly are we analyzing? An isolated feature, a product increment (EPIC), a feature set, or the product as a whole?"
Q2 — Perceived threat:
"What's your main concern? Agentic AI erosion? A specific competitor? General market commoditization?"
If the user has already provided this context in the conversation, in an EPIC, or in .acumen.md — extract directly, don't re-ask.
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.
- 4d ago First seen · 309 lines · 43 tokens per session scan A d8eec99bfc82
defensibility is a skill published in the GitHub repository VGrss/Acumen (11 stars, last pushed 28d ago), licensed Apache-2.0. It adds 43 tokens to every session and 3,444 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.
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…