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 agentmods add instructions/qmediat/gemini-code-context-mcp/claude-mdgit clone --depth 1 https://github.com/qmediat/gemini-code-context-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/qmediat/gemini-code-context-mcp/claude-md)<a href="https://agentmods.dev/instructions/qmediat/gemini-code-context-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/qmediat/gemini-code-context-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.00647 | $0.00647 |
| Opus 5 | $0.00324 | $0.00324 |
| Sonnet 5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
gemini-code-context-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 4d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo guidance for AI assistants
This file is checked into a public open-source repository. Anything you write here ships with the package.
Audience
Everything you produce in this repo — code, comments, commit messages, documentation, error strings, log lines — is read by external contributors and end users. Write for the world, not for an internal team.
- No references to private infrastructure, internal paths (
/Users/<name>/...), private repos, or non-public team members. - No assumptions about reader's prior context with the codebase. New contributors land here cold.
- Names, examples, and stack traces in docs use generic placeholders (
/path/to/...,your-org/your-repo) unless the example genuinely is@qmediat.io/....
Quality bar
- TypeScript strict, no
any, no default exports. See CONTRIBUTING.md. npm run lint && npm run typecheck && npm testmust pass before any commit.- Add a changeset (
npx changeset) for any user-visible change. - See PLAN.md for active work and docs/KNOWN-DEFICITS.md / docs/FOLLOW-UP-PRS.md for tracked debt.
Local dev gotcha — npx fails inside this repo
npx -y @qmediat.io/gemini-code-context-mcp (the invocation the README recommends to end users) fails when run from inside this repo's working directory:
sh: gemini-code-context-mcp: command not found
Reason: this repo's package.json declares the same name as the npm package. npx treats the source repo as the install target, finds no matching bin in local node_modules/.bin/, and bails. The package itself is fine — end users running from their own project dirs never see this.
Recommended patterns for maintainers (any of these avoids the conflict):
- Global install (simplest, decoupled from the repo entirely):
npm install -g @qmediat.io/gemini-code-context-mcp # MCP config: "command": "gemini-code-context-mcp" - Point MCP host at the local build — see
CONTRIBUTING.md→ Local MCP setup. Usenode ./dist/index.jsso no npx resolution happens. - Run
npx -yfrom outside the repo — setcwdin your MCP config to anywhere that isn't a sibling/parent of this repo.
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.
- 4d ago First seen · 45 lines · 647 tokens per session scan A 364ffe8f899e
gemini-code-context-mcp CLAUDE.md is an instructions file published in the GitHub repository qmediat/gemini-code-context-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 647 tokens to every session, about $0.0032 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
AionUi AGENTS.md
AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
botmux CLAUDE.md
Claude Code instructions for deepcoldy/botmux, covering botmux, 构建 & 运行, bun 开发链路, worktree 的 nodemodules：共享还是独立（改前必读） and 编译态（单文件二进制）注意.
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
SearChat CLAUDE.md
Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.
happier CLAUDE.md
Claude Code instructions for happier-dev/happier, covering claude code and typescript commands.