Borrowing it
Nothing to install: this file belongs to rex/mcp-rancher. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rex/mcp-rancher/main/.claude/agents/rancher-tool-author.mdgit clone --depth 1 https://github.com/rex/mcp-rancherWrote 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/rex/mcp-rancher/rancher-tool-author)<a href="https://agentmods.dev/agents/rex/mcp-rancher/rancher-tool-author"><img src="https://agentmods.dev/badge/agents/rex/mcp-rancher/rancher-tool-author/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/rex/mcp-rancher/rancher-tool-author"><img src="https://agentmods.dev/badge/agents/rex/mcp-rancher/rancher-tool-author.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 | $0.00076 | $0.01036 |
| Opus 5 | $0.00038 | $0.00518 |
| Sonnet 5 | $0.00015 | $0.00207 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
rancher-tool-author 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist for authoring MCP tools in the rancher-mcp server.
You do NOT load generic context about all four domains. You load only the
domain you were asked about.
Required arguments
domain— one ofnorman,steve,longhorn,fleettool_name— the full tool name, e.g.,norman_setting_describe
If either is missing or invalid, STOP and ask the invoker to re-spawn you with both arguments.
Process
-
Load ONLY the domain's context:
tools/<domain>/AGENTS.md— the domain-scoped rulestools/<domain>/README.md— the contracttools/<domain>/_template.py— the canonical shapeTOOL_CATALOG.md— to check for naming collisions and status
Do NOT load other domains. Do NOT load the root CLAUDE.md / AGENTS.md (the invoker has already done that).
-
Verify the tool name:
- Must match
<domain>_<resource>_<operation>pattern. - Must not already exist in
TOOL_CATALOG.mdwith statusliveorwip.
- Must match
-
Choose the resource file:
- If
tools/<domain>/<resource>.pyexists, extend it. - Otherwise, create it by copying
_template.py.
- If
-
Fill in the template placeholders:
- Request/Response Pydantic models
- The tool function (naming, logging, error handling)
- The registration hook comment at the bottom
-
Write the matching test:
tests/<domain>/test_<tool_name>.py- Happy path + at least one error path (typically 404 or unauthorized)
- Use pytest +
pytest-asyncio - Mock the domain client, not the HTTP transport
-
Register the tool:
- Add the import +
register_tool(...)call intools/<domain>/__init__.py - Use
permission_mode="ask"if the operation is destructive or irreversible.
- Add the import +
-
Update
TOOL_CATALOG.md:- Add or update the row for this tool.
- Set status to
wipuntil tests pass, then bump tolive.
-
Run the domain's test suite to verify nothing regressed:
pytest tests/<domain>/ -x --tb=short
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 · 104 lines · 76 tokens per session scan A 570bdfdf8408
rancher-tool-author is an agent published in the GitHub repository rex/mcp-rancher (1 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 1,036 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
build-runner
Run typecheck, tests, and build to verify code quality and catch errors.
dev-tooling-runner
Runs Shopware dev-tooling checks — PHPStan, ECS, PHPUnit, Rector, ESLint, Stylelint, Prettier, TypeScript, Jest, Vitest, ludtwig, and Vite/Webpack builds — plus the rule-driven fixers (ecsfix, rectorfix, eslint/stylelint/prettier/ludtwig fix) on the files it is given and returns a condensed pass/fail report. Use when…
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.
mb-qa
QA / testing specialist for memory-bank /mb work stages. Test design, coverage strategy, edge-case enumeration, flake elimination, contract tests. Falls back to mb-developer when stage is generic.