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 skills add octavehq/lfgtm --skill auditgit clone --depth 1 https://github.com/octavehq/lfgtmWrote 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/octavehq/lfgtm/audit)<a href="https://agentmods.dev/skills/octavehq/lfgtm/audit"><img src="https://agentmods.dev/badge/skills/octavehq/lfgtm/audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/octavehq/lfgtm/audit"><img src="https://agentmods.dev/badge/skills/octavehq/lfgtm/audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 34 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 544 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00054 | $0.18878 |
| Opus 5 | $0.00027 | $0.09439 |
| Sonnet 5 | $0.00011 | $0.03776 |
| Haiku 4.5 | $0.00005 | $0.01888 |
Grade A, and why
audit 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 10d 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 — 1,471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/octave:audit - Library Health Check
Comprehensive audit of your Octave GTM library. This skill operates as three things:
- Gap analyzer — what's missing that would make agents smarter
- Overlap ID'er — what's redundant or splitting hairs unnecessarily
- Strategic thought partner — push and challenge on design choices
The goal is not just "is the library complete?" but "is the library well-designed for what agents need to do?"
Core operating principle: The audit is a coach, not a builder. Push the user to think deeper about their GTM design rather than auto-generating content. Opinions are good — but only the USER's well-considered opinions. More entities isn't better. Better entities are better. The audit's job is to ask the questions that draw out the right design, not to fill templates.
The Offering Bar — Offering vs. Core Feature
The single most consequential decision in the library is what earns its own offering. Get this wrong and everything downstream fragments: a workspace with eight "products" that are really one platform ends up with eight Motions, eight thin matrices, and agents wired to the wrong things. This bar is the spine of the audit — apply it in every mode.
Products, Services, and Solutions are the three offering types, and all three are held to the SAME high bar. (A Solution is just a mix of a product and a service — it does not get an easier bar.) Anything that does not clear the bar is a Core Feature (core_feature, oId cf_), linked under the offering it belongs to — not a new offering.
An item earns its own offering only if it stands on its own as a go-to-market motion. The signals that count are motion-level, not naming-level:
- Own quota / own line item sold on its own motion — a rep carries it separately.
- Distinct buyer — a different person owns the decision.
- Distinct go-to-market motion — you'd sell it through a different play, a different sales cycle.
- The separate-meeting test: you could book a completely separate sales meeting to sell it — separate conversation, separate deal, separate buyer.
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.
- 10d ago First seen · 1,471 lines · 54 tokens per session scan A d7ac125c6aaa
audit is a skill published in the GitHub repository octavehq/lfgtm (11 stars, last pushed 19d ago), licensed MIT. It adds 54 tokens to every session and 18,878 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…