Borrowing it
Nothing to install: this file belongs to feuerdev/keep-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/feuerdev/keep-mcp/main/.agents/skills/keep-mcp-evidence/SKILL.mdgit clone --depth 1 https://github.com/feuerdev/keep-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/skills/feuerdev/keep-mcp/keep-mcp-evidence)<a href="https://agentmods.dev/skills/feuerdev/keep-mcp/keep-mcp-evidence"><img src="https://agentmods.dev/badge/skills/feuerdev/keep-mcp/keep-mcp-evidence/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/skills/feuerdev/keep-mcp/keep-mcp-evidence"><img src="https://agentmods.dev/badge/skills/feuerdev/keep-mcp/keep-mcp-evidence.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 | $0.00043 | $0.01324 |
| Opus 5 | $0.00022 | $0.00662 |
| Sonnet 5 | $0.00009 | $0.00265 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
keep-mcp-evidence 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
keep-mcp evidence
Prove the action through the actual MCP client and verify its effect independently in Google Keep. Test output belongs in code blocks, never screenshot substitutes. Prefer a CLI-based MCP client when available. Use the current agent's connected MCP tools if they target the verified build, otherwise use a bounded CLI invocation such as Codex exec or Cursor CLI. Honour the user's client choice and record its name/version. A desktop client is a fallback, not a requirement.
Save the exact prompt and actual MCP call/result events as text. CLI transcripts belong in code blocks; client screenshots are optional. Google Keep screenshots still provide the independent visual evidence. Read cli-runs.md when using a CLI client.
Preflight
- Read the diff and choose concrete visible outcomes. Read scenarios.md for the checklist scenarios from PR #19.
- Verify the client's keep-mcp launch command resolves to the checkout/build under test. Record commit, dirty status, interpreter, SDK version and transport without logging environment values. Restart/reconnect the server after changes. A checked out commit alone does not establish which server an already-running client uses.
- If multiple Keep servers are configured, target the exact server under test and inspect every invocation. Do not silently fall back to another server.
- Open Google Keep in an isolated authenticated browser session when available. Confirm it is the same account as the configured server, without publishing the account identifier. Prefer a dedicated test account. If login is needed, leave the page open and ask the user to sign in. Continue independent preparation while waiting. Never request tokens/passwords in chat or copy browser credentials.
- Use
UNSAFE_MODE=false. Operate only on fixtures created for this run, with nameskeep-mcp-evidence-<UTC timestamp>-<random suffix>-<scenario>. Record returned note IDs immediately. Keep a local manifest of IDs and cleanup status. Never delete unrelated notes or the sharedkeep-mcplabel.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 99 lines · 43 tokens per session scan A ed28044ffe7d
keep-mcp-evidence is a skill published in the GitHub repository feuerdev/keep-mcp (100 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 1,324 once invoked, about $0.0002 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 2026-09-10.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…