Borrowing it
Nothing to install: this file belongs to Considus/pagespeed-insights-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/Considus/pagespeed-insights-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Considus/pagespeed-insights-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/considus/pagespeed-insights-mcp/agents-md)<a href="https://agentmods.dev/instructions/considus/pagespeed-insights-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/considus/pagespeed-insights-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/considus/pagespeed-insights-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/considus/pagespeed-insights-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 | $0.01097 | $0.01097 |
| Opus 5 | $0.00549 | $0.00549 |
| Sonnet 5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
pagespeed-insights-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 yesterday.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent notes
For a coding agent working in this repo. CONTRIBUTING.md is the human document and it is not duplicated here; read it first for the ground rules and the release order. This file is the part an agent needs and a person already knows.
Every task moves through four beats: isolate on a branch, build, prove with evidence, ship a PR carrying that evidence.
Isolate
Branch from origin/main by name, never from wherever HEAD is sitting, and check nobody is already on the work:
git fetch origin
gh pr list -R Considus/pagespeed-insights-mcp
git checkout -b <type>/<short-name> origin/main
If an open PR touches the same files, build on it or say so and stop. Stage by explicit path. Never git add -A.
Build
Read CONTRIBUTING.md before writing. Three things there are constraints rather than preferences, and a change that breaks one is rejected however good the rest is.
- Standard library only, with no optional-dependency escape hatch. This is what lets someone who does not use a terminal download the package and run it, and it is why the service-account credential was dropped for an API key.
- No number without its uncertainty. Every figure is a median across distinct analyses with its min-max spread beside it, and runs PSI served from cache are dropped and counted.
- Lab and field stay separate. Lighthouse is a simulation, CrUX is what real people got. They disagree by an order of magnitude and merging them destroys the only honest thing here.
Python 3.9 is the floor. CI runs 3.9 and 3.12 on Linux, macOS and Windows. A 3.10-only construct (match, a runtime-evaluated X | Y annotation, zip(strict=), itertools.pairwise, tomllib, dataclass(slots=)) passes on your interpreter and fails only in the 3.9 leg. Windows is in the matrix on purpose: being installable there without a compiled dependency is a property that would regress silently.
manifest.json is generated. The version lives in pagespeed_insights/__init__.py and the tool list lives in the package. ./build-mcpb.py --sync writes both across. Never hand-edit the manifest. Every tool needs a title and the right readOnlyHint or destructiveHint; a directory submission is rejected without them, and report is the one tool that is not read-only because it writes a file.
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.
- yesterday First seen · 67 lines · 1,097 tokens per session scan A 140a20522813
pagespeed-insights-mcp AGENTS.md is an instructions file published in the GitHub repository Considus/pagespeed-insights-mcp (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,097 tokens to every session, about $0.0055 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 2026-09-18.
Other instructions, from other repositories
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).
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.
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.
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.
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).