Borrowing it
Nothing to install: this file belongs to guipmilek/bundled-notes-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/guipmilek/bundled-notes-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/guipmilek/bundled-notes-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/guipmilek/bundled-notes-mcp/agents-md)<a href="https://agentmods.dev/instructions/guipmilek/bundled-notes-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/guipmilek/bundled-notes-mcp/agents-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/guipmilek/bundled-notes-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/guipmilek/bundled-notes-mcp/agents-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 | $0.00770 | $0.00770 |
| Opus 5.5 | $0.00308 | $0.00308 |
| Sonnet 5.5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
bundled-notes-mcp AGENTS.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 2mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bundled Notes MCP - Agent Instructions
Project
Unofficial Python/FastMCP server for Bundled Notes Web. Source lives under
src/bundled_notes_mcp/; tests live under tests/. Supported runtimes are local
stdio and user-owned Prefect Horizon deployments. Every user must fork the
repository and publish one deployment per account; never advertise or reuse a
maintainer or third-party endpoint.
Mandatory rules
- Read
llms.txtanddocs/agent-playbook.mdbefore non-trivial changes. - Keep every write/destructive tool gated by
confirm: true. - Keep MCP behavior annotations explicit and accurate.
- Never commit
.env, credentials, refresh/ID tokens, sessions, API responses, private note contents, attachment files, or Firebase download tokens. - Never accept a Bundled Notes password as an MCP tool argument.
- Preserve unknown Firestore fields with partial updates.
- Re-read confirmed writes and keep compensating cleanup for multi-step mutations.
- Update docs and
llms.txtwhen architecture, commands, tools, or security change. - Use only uniquely prefixed disposable records for live integration tests and verify their removal afterward.
- Keep Horizon authentication enabled and MCP request/response payload logging disabled; production data can contain private notes and attachment metadata.
- Before adapting to a Bundled Notes release, run the sanitized schema audit and
follow
docs/schema-maintenance.md; never commit rollout/session exports.
Workflow
- Confirm repository, branch, and working-tree scope.
- Classify the change and read its owning module plus the relevant document.
- For upstream changes, run the sanitized schema audit before any live write.
- Implement the smallest compatible change with focused positive and negative tests.
- Run the full verification ladder and update both READMEs,
llms.txt,WRITES.md, and relevant docs when public behavior changes. - Use disposable prefixed records for an authorized live audit, then prove baseline restoration.
- Publish through the approved GitHub workflow and stop before merge pending owner approval.
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.
- 2mo ago First seen · 76 lines · 770 tokens per session scan A 3537e7b84d34
bundled-notes-mcp AGENTS.md is an instructions file published in the GitHub repository guipmilek/bundled-notes-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 770 tokens to every session, about $0.0031 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 2026-08-31.
bundled-notes-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bundled-notes-mcp AGENTS.mdguipmilek/bundled-notes-mcp | Instructions file | 0 | 2mo ago | MIT | A | 770 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |