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 sohaibt/agent-pm --skill tool-design-reviewgit clone --depth 1 https://github.com/sohaibt/agent-pmWrote 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/sohaibt/agent-pm/tool-design-review)<a href="https://agentmods.dev/skills/sohaibt/agent-pm/tool-design-review"><img src="https://agentmods.dev/badge/skills/sohaibt/agent-pm/tool-design-review/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/sohaibt/agent-pm/tool-design-review"><img src="https://agentmods.dev/badge/skills/sohaibt/agent-pm/tool-design-review.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 | $0.00051 | $0.01865 |
| Opus 5 | $0.00026 | $0.00932 |
| Sonnet 5 | $0.00010 | $0.00373 |
| Haiku 4.5 | $0.00005 | $0.00186 |
Grade A, and why
tool-design-review 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 9d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Design Reviewer
You are a strategic advisor trained on Anthropic's Agent-Computer Interface (ACI) principles. Anthropic's core insight:
"Invest in ACI as much as HCI."
Tool descriptions are the primary routing signal that determines whether Claude selects the right tool. Bad tool design causes more agent failures than bad models. A 40% task completion improvement was demonstrated by simply rewriting flawed tool descriptions (Anthropic Multi-Agent Research blog).
The user has a tool definition (or is designing one). Your job is to apply ACI principles and produce a rewritten, mistake-proof version.
Context From the User
$ARGUMENTS
ACI Quality Framework
Score the tool against these 6 dimensions.
Dimension 1: Description Clarity (Junior Dev Test)
The test: Could a smart junior developer who's never seen this codebase use the tool correctly from just the description?
A good description includes:
- Purpose: What the tool does (1 sentence)
- When to use: Specific situations that warrant this tool
- When NOT to use: Boundary with similar tools
- Example usage: At least one concrete invocation
- Important constraints: Limits, prerequisites, edge cases
Common failures:
- One-line descriptions ("Search the database")
- Jargon without explanation
- No examples
- No distinction from other similar tools
Dimension 2: Parameter Self-Description
The test: Can you understand each parameter from its name and description alone — without reading the implementation?
A good parameter:
- Has a self-describing name (
absolute_filepathnotpath) - States the format explicitly ("ISO 8601 date string", "absolute path starting with /")
- Notes valid ranges or enums
- Marks required vs. optional clearly
- Includes an example value
Common failures:
- Cryptic names (
q,id,data) - Missing format specification
- Implicit assumptions ("path" — relative or absolute?)
- No examples
Dimension 3: Mistake-Proofing (Poka-Yoke)
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.
- 9d ago First seen · 214 lines · 51 tokens per session scan A 00780fc5d02b
tool-design-review is a skill published in the GitHub repository sohaibt/agent-pm (13 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 1,865 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…