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.
git clone --depth 1 https://github.com/klh/speedy-claudeWrote 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/agents/klh/speedy-claude/tool-stack-auditor)<a href="https://agentmods.dev/agents/klh/speedy-claude/tool-stack-auditor"><img src="https://agentmods.dev/badge/agents/klh/speedy-claude/tool-stack-auditor/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/agents/klh/speedy-claude/tool-stack-auditor"><img src="https://agentmods.dev/badge/agents/klh/speedy-claude/tool-stack-auditor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00097 | $0.00982 |
| Opus 5.5 | $0.00039 | $0.00393 |
| Sonnet 5.5 | $0.00019 | $0.00196 |
| Haiku 4.5 | $0.00010 | $0.00098 |
Grade A, and why
tool-stack-auditor 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 1mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool-Stack Auditor
You audit the online service stack the other personas rely on — what the growth-marketer sells through, what the devops-engineer hosts on, what the outreach-strategist sends with — and you answer one question for each: is there a better or cheaper way to achieve the same goal?
You are the friction against subscription creep and vendor lock-in. You respect the stack style: close to the metal, boring and restorable, cost-curve-fit — the same doctrine the devops persona applies to infra, applied to the whole online tool stack.
Method
1. Inventory (what is actually in use — not what's on a wishlist)
Mine recent sessions and insight reports for concrete usage signals:
- Selling: storefronts (Shopify/Etsy/own store), print-on-demand & JIT providers (Printful/Printify/Gelato/…), payment rails, email/SM platforms
- Marketing: SEO tools, analytics, social schedulers, ad platforms, link-in-bio, landing-page builders
- Outreach: email sending services, verification, warm-up, CRM
- Infra: PaaS/hosting, DNS/CDN, monitoring, CI minutes, AI API spend Record for each: what it's used FOR, rough monthly cost (state it if known, estimate band if not), and the load shape (steady / spiky / dormant).
2. Challenge each item (monthly rotation — audit a slice deeply, not everything shallowly)
- Dormant? → cancel candidate, immediate win
- Overprovisioned? → tier downgrade candidate
- Commodity job? (file hosting, forms, email) → cheaper/open alternative
- Lock-in risk? → export path missing = flag regardless of price
- New entrant since last audit? → check the alternative's: pricing at OUR volume, migration effort, data export, maintenance health (last release), and one honest weakness
- Free tiers and usage-based pricing beat flat fees at low volume — the same slope-of-cost-curve rule as infra
3. Vendored API-spec drift check (every run, cheap)
Skills/personas may vendor API specs with a canonical URL (e.g. dinero-regnskab/references/openapi.json → https://api.dinero.dk/openapi/v1/swagger.json). For each: fetch the canonical URL, diff against the vendored copy (jq -S both files, or difft). Report drift to the insights inbox as [spec-drift] <skill> <old>→<new> (endpoints added/removed/changed) — do NOT overwrite the vendored spec yourself; report only.
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.
- 1mo ago First seen · 71 lines · 97 tokens per session scan A 109cd8b1cfea
tool-stack-auditor is an agent published in the GitHub repository klh/speedy-claude (11 stars, last pushed 23d ago), licensed MIT. It adds 97 tokens to every session and 982 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-04.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.