Borrowing it
Nothing to install: this file belongs to jarmstrong158/skillmatch-mcp. 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/jarmstrong158/skillmatch-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/jarmstrong158/skillmatch-mcpWrote 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/instructions/jarmstrong158/skillmatch-mcp/claude-md)<a href="https://agentmods.dev/instructions/jarmstrong158/skillmatch-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jarmstrong158/skillmatch-mcp/claude-md/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/instructions/jarmstrong158/skillmatch-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jarmstrong158/skillmatch-mcp/claude-md.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 | $0.02119 | $0.02119 |
| Opus 5 | $0.01059 | $0.01059 |
| Sonnet 5 | $0.00424 | $0.00424 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade A, and why
skillmatch-mcp CLAUDE.md 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 8d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SkillMatch MCP Server
SkillMatch is a job search assistant for people who demonstrate their skills through actual work (GitHub repos, project portfolios) rather than credentials alone. It helps Claude analyze job fit, track applications, and build targeted search queries.
Onboarding Flow
The first time a user interacts with SkillMatch, there will be no profile. When get_profile returns the "no profile" error, walk the user through onboarding by asking the setup questions conversationally, then call setup with all their answers at once.
Questions to ask during onboarding:
- What is your name?
- What is your current role or situation?
- What roles are you targeting? (collect as a list)
- What is your minimum acceptable salary? (integer)
- Are you only looking for remote positions?
- What is your location?
- What are your dealbreakers? (collect as a list)
- What is your GitHub profile URL?
- Where is your resume file? (absolute path, supports .txt, .md, .docx — OR paste resume text directly)
- (Optional) What is your LinkedIn profile URL?
Tools
setup
Saves the user's profile to data/profile.json. If a profile already exists, the tool returns the existing profile and requires confirm_overwrite: true to replace it. Always ask the user before overwriting.
get_profile
Returns the saved profile. Call this at the start of a conversation to check if onboarding is needed. If no profile exists, trigger the onboarding flow.
get_portfolio
Fetches the user's public GitHub repos via the GitHub API (no auth needed). Returns repo name, description, language, topics, last updated, and homepage. Skips forks. Sorted by last updated. Use this when the user asks about their portfolio or when analyzing job fit.
get_resume
Reads the resume file from the path stored in the profile. Returns raw text content. Supports .txt, .md, and .docx formats. Use this when the user asks about their resume or when analyzing job fit.
search_jobs
Does NOT search the web. Accepts a query string and combines it with the user's profile (target roles, salary floor, remote preference, location) to build an optimized search query. Returns the query string and filtering instructions. After calling this tool, use the returned query with a web search tool to find actual listings.
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.
- 8d ago First seen · 136 lines · 2,119 tokens per session scan A ede35d058b8b
skillmatch-mcp CLAUDE.md is an instructions file published in the GitHub repository jarmstrong158/skillmatch-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,119 tokens to every session, about $0.0106 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.