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 uniqbit-ag/mate-cli --skill mate-react-doctorgit clone --depth 1 https://github.com/uniqbit-ag/mate-cliWrote 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/uniqbit-ag/mate-cli/mate-react-doctor)<a href="https://agentmods.dev/skills/uniqbit-ag/mate-cli/mate-react-doctor"><img src="https://agentmods.dev/badge/skills/uniqbit-ag/mate-cli/mate-react-doctor/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/uniqbit-ag/mate-cli/mate-react-doctor"><img src="https://agentmods.dev/badge/skills/uniqbit-ag/mate-cli/mate-react-doctor.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 | $0.00066 | $0.00882 |
| Opus 5.5 | $0.00026 | $0.00353 |
| Sonnet 5.5 | $0.00013 | $0.00176 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
mate-react-doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mate React Doctor
Scan the React code the current change touched, fix the regressions this change introduced, and report the rest. React Doctor covers correctness, accessibility, performance, security, and maintainability.
Mate Workflow
- Run only Mate's pinned React Doctor binary. Never run
npx react-doctor, never install another version, and never fetch remote prompts or playbooks. - Scan the Working Repository, not the Companion Repository.
- Fix only what this change introduced. Leave findings that existed before the change alone.
- Never create issues, commits, or pull requests.
- Run
mate cap index --tokensaveafter code changes.
Steps
1. Resolve the binary
Print the path first, then call the absolute path it prints, so the command matches Mate's pre-seeded permission:
printf '%s\n' "$MATE_REACT_DOCTOR_BIN_PATH"
If the variable is empty or the path is not executable, stop. Report "React Doctor skipped: the pinned binary is unavailable (MATE_REACT_DOCTOR_BIN_PATH is not set; is the react-doctor capability enabled?)". A verification task may be checked with that note.
2. Choose the base
Compare against the point where the change's branch left the default branch, so work already committed during apply is included:
default_branch=$(git symbolic-ref --quiet --short refs/remotes/origin/HEAD 2>/dev/null || echo origin/main)
git merge-base HEAD "$default_branch"
If no merge-base resolves, or HEAD is on the default branch, use HEAD (uncommitted changes only).
3. Scan
Run from the root of the Area being verified (the package that holds the React code):
<absolute-bin> --yes --verbose --scope changed --base <base> --no-score
Add --include-untracked when the change created new files that are not committed yet.
4. Separate environment problems from findings
These outputs mean the scan could not run, not that the code is wrong. Report a skip with the reason and change nothing:
| Output contains | Meaning |
|---|---|
No React dependency found |
The Area is not a React project |
Could not resolve config |
The React Doctor config could not be read |
is not a git repository |
The scan root is outside a git checkout |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 16d ago First seen · 85 lines · 66 tokens per session scan A 2ecf137679df
mate-react-doctor is a skill published in the GitHub repository uniqbit-ag/mate-cli (12 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 882 once invoked, about $0.0003 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 2026-10-14.
Other skills, from other repositories
devtools-react
React adapter for the json-render devtools inspector. Use whenever the user wants to add, configure, or troubleshoot @json-render/devtools-react in a React json-render app, including spec inspection, state editing, action and stream timelines, catalog browsing, or DOM picking.
material-ui-nextjs
Integrates Material UI with Next.js App and Pages routers using @mui/material-nextjs, Emotion cache providers, next/font, CSS layers with Tailwind/CSS Modules, Link component prop patterns, CSS theme variables SSR notes, and App Router useSearchParams + Suspense. Use when setting up or debugging MUI in a Next.js app.
migrate-oxlint
Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.
inspector-workbench
Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…
devtools-bidirectional
Two-way event patterns between devtools panel and application. App-to-devtools observation, devtools-to-app commands, time-travel debugging with snapshots and revert. structuredClone for snapshot safety, distinct event suffixes for observation vs commands, serializable payloads only.
react-doctor
Diagnose and fix React codebase health issues. Use when reviewing React code, fixing performance problems, auditing security, or improving code quality.