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 adimango/ai-adoption-playbook --skill tool-stack-auditgit clone --depth 1 https://github.com/adimango/ai-adoption-playbookWrote 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/adimango/ai-adoption-playbook/tool-stack-audit)<a href="https://agentmods.dev/skills/adimango/ai-adoption-playbook/tool-stack-audit"><img src="https://agentmods.dev/badge/skills/adimango/ai-adoption-playbook/tool-stack-audit.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 5.1 | $0.00031 | $0.01605 |
| Opus 5 | $0.00015 | $0.00803 |
| Sonnet 5 | $0.00006 | $0.00321 |
| Haiku 4.5 | $0.00003 | $0.00161 |
Grade A, and why
tool-stack-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 7d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Stack Audit
Purpose
Structured audit of a team's AI tools: what they have, what's used, what's wasted, and what's missing. Produces a clear inventory with cost analysis. This is an audit, not a shopping list — it evaluates what exists before recommending changes.
Core principle: Audit what you have before buying what you don't. Most teams have more tools than they use and more overlap than they realize.
Context Intake
For Department: and Currency:, use the first available source: the current fluency scorecard → adoption.local.md (the department this run covers; by default the one marked (primary) — see CLAUDE.md Local Configuration) → ask the leader (currency defaults to USD).
Process
Required Inputs
- Tool list: Every AI tool the team pays for (team licenses and individual subscriptions)
- Per tool: Cost, number of seats, who uses it, what for, how often
- Overlap: Any tools that do similar things
- Gaps: Tasks where people want AI help but don't have a tool
Audit Criteria
Evaluate each tool against four questions:
| Question | What you're looking for |
|---|---|
| Is it used? | Weekly active users vs. seats paid for |
| Is it the right tool for the job? | Does it match the actual use case, or was it bought for a different purpose? |
| Does it overlap with another tool? | Two tools doing the same thing = one should go |
| Is it governed? | Does the company control the account, or is it an individual subscription? |
Output
Produce the audit in this exact format. Currency note: Substitute the [CCY] placeholder below with the currency symbol from the fluency-assessment scorecard ($ for USD, € for EUR, £ for GBP, etc.). If no scorecard is available, ask the founder which currency they report in.
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.
- 7d ago First seen · 149 lines · 31 tokens per session scan A 50746ebdd5bc
tool-stack-audit is a skill published in the GitHub repository adimango/ai-adoption-playbook (23 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,605 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.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…