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/stickerdaniel/linkedin-mcp-server/agents-mdgit clone --depth 1 https://github.com/stickerdaniel/linkedin-mcp-serverWrote 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/stickerdaniel/linkedin-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/stickerdaniel/linkedin-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/stickerdaniel/linkedin-mcp-server/agents-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 | $0.04959 | $0.04959 |
| Opus 5 | $0.02479 | $0.02479 |
| Sonnet 5 | $0.00992 | $0.00992 |
| Haiku 4.5 | $0.00496 | $0.00496 |
Grade A, and why
linkedin-mcp-server AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -D /tmp/mcp-headers -X POST http://127.0.0.1:8000/mcp \ Copies of this mod
1 near-identical copy found in the catalogue:
- lubot-hunter-mcp-2026 AGENTS.md — 100% identical, 24 lines differ
How it starts
The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Development Commands
- Use
uvfor dependency management:uv sync(dev:uv sync --group dev) - Lint:
uv run ruff check .(auto-fix with--fix) - Format:
uv run ruff format . - Type check:
uv run ty check(using ty, not mypy) - Tests:
uv run pytest(with coverage:uv run pytest --cov) - Pre-commit:
uv run pre-commit installthenuv run pre-commit run --all-files - Run server locally:
uv run -m linkedin_mcp_server --no-headless - Run via uvx (PyPI/package verification only):
uvx mcp-server-linkedin - Docker build:
docker build -t linkedin-mcp-server . - Install browser:
uv run patchright install chromium
Scraping Rules
- One section = one navigation. Each entry in
PERSON_SECTIONS/COMPANY_SECTIONS(scraping/fields.py) maps to exactly one page navigation. Never combine multiple URLs behind a single section. - Minimize DOM dependence. Prefer innerText and URL navigation over DOM selectors. When DOM access is unavoidable, use minimal generic selectors (
a[href*="/jobs/view/"]) — never class names tied to LinkedIn's layout. - Detection must be locale-independent. Classification logic — connection state, action availability, button identity — must rely on URL patterns (
/preload/custom-invite/?vanityName=USER,/in/USER/edit/intro/,/messaging/compose/), attribute presence (aria-labelexists,aria-expandedexists,aria-disabledexists), or structural counts — never on text values like "Connect", "Follow", "Message", "1st", "Pending". The verb in anaria-labelis locale-dependent; whether the attribute exists is not. Where text is genuinely the only signal, guard it behind an explicit per-locale table and document the limitation in code.
Browser Identity Rules
- The browser must not contradict itself. Anything it says about itself has
to survive being checked against another surface of the same browser: the
user-agent against
sec-ch-ua, the page against its workers and iframes, the reported screen against the window sitting on it. The goal is coherence, not invisibility — invisibility cannot be proven, while a contradiction is a fact and can be found by anyone who looks twice. - Never inject a fingerprint. No
user_agent, no custom headers, no spoofed client hints. Patchright's own guidance says the same, and every override measured here made things worse: auser_agent=argument changes the string but not the client hints, and never reaches service workers at all (playwright#5237, closed as an upstream Chromium bug). A browser telling the truth beats one caught lying. - A proxy must contain every egress path, not just HTTP. WebRTC uses UDP
and went around a configured proxy until the switches in
browser_launch.py. DNS and QUIC belong to the same family; check them before assuming a new setting is contained. - Verify identity changes by measurement.
docs/browser-fingerprint.mdlists the four detectors, what each one alone would miss, and the values measured so far. A launch-configuration change without a measurement against them is a guess.
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 Changed · +24 lines · +302 tokens per session d7ad67fa8d30
- 4d ago First seen · 306 lines · 4,657 tokens per session scan A 60622bd6c1ef
linkedin-mcp-server AGENTS.md is an instructions file published in the GitHub repository stickerdaniel/linkedin-mcp-server (3,303 stars, last pushed 2d ago), licensed Apache-2.0. It adds 4,959 tokens to every session, about $0.0248 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
pagespeed-insights-mcp AGENTS.md
AGENTS.md instructions for ruslanlap/pagespeed-insights-mcp, covering project rules — pagespeed-insights-mcp (mcp server), специфіка проєкту, обов'язкові практики (mcp + ts), serena + .serena/ and професійні skills тільки.
kafka-schema-reg-mcp AGENTS.md
AGENTS.md instructions for aywengo/kafka-schema-reg-mcp, covering development guidelines, prerequisites, quick setup, install dependencies and install dev dependencies (optional but recommended).
ls-mcp AGENTS.md
AGENTS.md instructions for lirantal/ls-mcp, covering agents.md, start here, documentation, prs and issues and releases.
PBP CLAUDE.md
Instructions for MadGapun/PBP, covering pbp — claude-code-memory, stand 2026-08-25 (v1.7.23 stable) — ehrliche zahlen, stand 2026-07-16 (v1.8.0-beta.6, prerelease) — hotfix #760, stand 2026-07-14 (v1.7.7) — scoring-fairness & praxis-funde and stand 2026-07-03 (v1.7.6) — alltags-fuehrung.
mcp-standardnotes CLAUDE.md
Claude Code instructions for lozit/mcp-standardnotes, covering mcp standard notes, stack, commands, structure and exposed mcp tools.
Instability CLAUDE.md
Instructions for tcpiplab/Instability, covering claude.md, commands, code style guidelines & design philosophy, v3 project architecture and core components (v3).