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/gemini-cli-extensions/developer-knowledge/gemini-mdgit clone --depth 1 https://github.com/gemini-cli-extensions/developer-knowledgeWhat 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 | $0.00612 | $0.00612 |
| Opus 5 | $0.00306 | $0.00306 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
developer-knowledge GEMINI.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 2d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeveloperKnowledge MCP Server
This server provides access to documentation about Google developer products. It can search for relevant documents based on a query and retrieve the full content of those documents.
Tools
search_documents
This is the primary tool to search for documentation. It returns snippets of
relevant documents, along with their names and URLs. If snippets are
insufficient, use get_documents to retrieve full content.
When to use:
- Use this tool as the first step when a user asks a question about one of the covered Google developer products and you need to find relevant documentation.
When not to use:
- Do not use this tool if the user's question is not related to one of the covered Google developer products.
- Do not use this tool if you already have a document name and need its
content; use
get_documentsinstead.
Example: If a user asks "How do I create a Cloud Storage bucket?", you
should call: print(developer_knowledge.search_documents(query="How to create a Cloud Storage bucket?"))
answer_query
Use this tool to let another model search for content and synthesize an answer.
This can save tokens in your own context window. This can be helpful for
summarizing complex results. answer_query returns citations for its response.
If needed, you can fetch the full content of the citations using
get_documents, just like you can with search_documents.
When to use:
- Use this to synthesize complex information without using as many tokens as
search_documents.
When not to use:
- Do not use this tool if the user's question is not related to one of the covered Google developer products.
- Do not use this tool if you already have a document name and need its
content; use
get_documentsinstead.
get_documents
This tool retrieves the full content of multiple documents (up to 20) in a single call, based on their names.
When to use:
- After calling
search_documents, if multiple results seem relevant but their snippets are insufficient to answer the user's question, use this tool to retrieve the full document content of up to 20 results in a single call, using theparentreturned bysearch_documents.
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.
- 2d ago First seen · 74 lines · 612 tokens per session scan A e3b1c4c540d6
developer-knowledge GEMINI.md is an instructions file published in the GitHub repository gemini-cli-extensions/developer-knowledge (8 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 612 tokens to every session, about $0.0031 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 instructions, from other repositories
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit 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.
langchain 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.