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/larsbaunwall/unlinked/agents-mdgit clone --depth 1 https://github.com/larsbaunwall/UnlinkedWhat 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 | $0.01155 | $0.01155 |
| Opus 5 | $0.00577 | $0.00577 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
Unlinked 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 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Purpose
This repository is Unlinked, a TypeScript MCP server that connects a user's LinkedIn professional profile and experience data to AI assistants such as Claude Desktop, GitHub Copilot, and other Model Context Protocol clients.
Unlinked exists to let a member bring their own professional context into an assistant without making the assistant scrape LinkedIn, infer profile details, or rely on stale manually copied text. The LinkedIn API surface used here is read-only.
Core Requirements
- Build the server with the official TypeScript MCP SDK,
@modelcontextprotocol/sdk. - Run the MCP server from the CLI over stdio with
StdioServerTransport. - Keep the project usable by desktop MCP clients, especially Claude Desktop and GitHub Copilot.
- Connect to LinkedIn's Member Data Portability (Member) API product.
- Fetch LinkedIn member profile and professional-history data for the authenticated member.
- Treat the LinkedIn access token as a startup secret. Read it from the
LINKEDIN_TOKENenvironment variable. Use it only to sendAuthorization: Bearer <access_token>to LinkedIn. Do not persist it, log it, echo it into MCP responses, or put it in package scripts. - Make clear in user-facing docs and errors that the Member Data Portability product is currently available only to LinkedIn members in the European Economic Area and Switzerland.
- Preserve the API's read-only nature. Do not add tools that mutate LinkedIn data.
LinkedIn API Notes
The main documentation is LinkedIn's Microsoft Learn page for Member Data Portability (Member).
Before implementing or changing LinkedIn API behavior, also read the local skill at .agents/skills/linkedin-member-data-portability/SKILL.md.
Important behavior from the docs:
- Access requires a LinkedIn Developer application provisioned with the Member Data Portability API (Member) product.
- The OAuth Token Generator flow is currently available only to members located in the EEA and Switzerland.
- The token generator documentation currently instructs members to request the
r_dma_portability_self_servescope. The Snapshot and Changelog API pages also describe DMA portability permissions such asr_dma_portability_memberandr_dma_portability_3rd_party. Follow the current docs and surface authorization failures clearly. - The LinkedIn API version is configured with
LINKEDIN_API_VERSIONand defaults to202312when unset. The value must be inYYYYMMformat (e.g.202312,202501). Do not usev2or any other non-date format. - Snapshot data is fetched with
GET https://api.linkedin.com/rest/memberSnapshotData?q=criteriaand optionaldomainquery parameter. - Professional profile domains to prioritize include
PROFILE,POSITIONS,EDUCATION,SKILLS,CERTIFICATIONS,PROJECTS,ORGANIZATIONS,LANGUAGES,HONORS,COURSES,PUBLICATIONS,PATENTS,VOLUNTEERING_EXPERIENCES, andRECOMMENDATIONS. - Snapshot responses may be paginated. Follow
paging.linksuntil no next page remains, and account for the docs' warning thatpaging.totalmay not fully reflect all pages. - Changelog events are fetched with
GET https://api.linkedin.com/rest/memberChangeLogs?q=memberAndApplication. They cover events generated after member consent and are currently limited to the past 28 days. - Changelog polling should support
startTime, use the latest returnedprocessedAtas the next cursor, default to modest page sizes, and respect the documented uppercountlimit of 50. - LinkedIn errors use standard HTTP status codes and JSON bodies with
message,serviceErrorCode, andstatus. Return helpful MCP errors without leaking tokens.
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 · 63 lines · 1,155 tokens per session scan A 1dcebbe89e92
Unlinked AGENTS.md is an instructions file published in the GitHub repository larsbaunwall/Unlinked (3 stars, last pushed 3mo ago), licensed MIT. It adds 1,155 tokens to every session, about $0.0058 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 2026-08-31.
Other instructions, from other repositories
linkedin-mcp-server AGENTS.md
AGENTS.md instructions for stickerdaniel/linkedin-mcp-server, covering claude.md, development commands, scraping rules, browser identity rules and profile safety rules.
mcp-server-linkedin AGENTS.md
AGENTS.md instructions for Huzaifa-ali/mcp-server-linkedin, covering agents.md — ai development guidelines, repository map, architecture, key principles and code style.
linkedin-mcp-server CLAUDE.md
Claude Code instructions for stickerdaniel/linkedin-mcp-server, a project described as: Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.
veezee-mcp AGENTS.md
AGENTS.md instructions for veezeehq/veezee-mcp: This repo is the issue tracker for the hosted Veezee MCP server. To use the server, you don't need anything from this repo.
linkedctl CLAUDE.md
Claude Code instructions for alexey-pelykh/linkedctl, covering linkedctl — claude instructions, project overview, repository structure, package dependency graph and development commands.
AmplifyrMCP CLAUDE.md
Claude Code instructions for supersaiyane/AmplifyrMCP, covering claude.md — amplifyrmcp, project identity, golden rules, tech stack — exact versions and project structure.