Borrowing it
Nothing to install: this file belongs to tr4m0ryp/linkedin-mcp-server. 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/tr4m0ryp/linkedin-mcp-server/main/.agents/skills/2-repro-issue/SKILL.mdgit clone --depth 1 https://github.com/tr4m0ryp/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/skills/tr4m0ryp/linkedin-mcp-server/2-repro-issue)<a href="https://agentmods.dev/skills/tr4m0ryp/linkedin-mcp-server/2-repro-issue"><img src="https://agentmods.dev/badge/skills/tr4m0ryp/linkedin-mcp-server/2-repro-issue/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/tr4m0ryp/linkedin-mcp-server/2-repro-issue"><img src="https://agentmods.dev/badge/skills/tr4m0ryp/linkedin-mcp-server/2-repro-issue.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 | $0.00075 | $0.02584 |
| Opus 5 | $0.00037 | $0.01292 |
| Sonnet 5 | $0.00015 | $0.00517 |
| Haiku 4.5 | $0.00007 | $0.00258 |
Grade A, and why
2-repro-issue scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -D /tmp/repro-$NUM-headers -X POST http://127.0.0.1:$PORT/mcp \ This is a copy
100% identical to 2-repro-issue — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reproduce a LinkedIn-MCP Issue Locally
Goal: take an issue number, run the exact failing tool call against the real LinkedIn via the local MCP server, and produce concrete evidence — output JSON, error message, partial state — that confirms or refutes the bug on the current branch. Always use the authenticated profile already at ~/.linkedin-mcp/profile/. Never mock.
Phase 1 — Read and map
# Accept "442", "#442", or "https://github.com/.../issues/442" — extract the digits only
NUM=$(echo "$ARGUMENTS" | sed -E 's|.*/||; s|#||g' | grep -oE '^[0-9]+' | head -1)
[ -z "$NUM" ] && { echo "Invalid input: '$ARGUMENTS'. Pass an issue number or URL." >&2; exit 1; }
REPO=stickerdaniel/linkedin-mcp-server
gh issue view $NUM --repo $REPO --comments
From the issue body extract:
- Which MCP tool is affected (
get_person_profile,connect_with_person,search_jobs, …). The issue templates ask for this explicitly. - The exact arguments that trigger the failure (username, company slug, job ID, sections list).
- The expected vs actual behaviour.
- Any locale signal — German UI, non-English profile name, RTL language. Locale-sensitive bugs need a deliberately diverse target.
Map the tool to code so you know where to look if the repro confirms the bug:
linkedin_mcp_server/tools/<surface>.py— MCP entrypoint and arg validationlinkedin_mcp_server/scraping/<feature>.py— actual scraping (extractor.py,connection.py,feed.py,inbox.py, …)linkedin_mcp_server/scraping/fields.py—PERSON_SECTIONS/COMPANY_SECTIONS(each entry = one navigation)- Existing test in
tests/test_scraping.pycovering the same surface
State out loud before running anything: "Reproducing tool X with args Y on branch <current> — expecting <failure mode from issue>."
Phase 2 — Confirm session, branch, dependencies
git status --porcelain | head -5 # workspace must be clean
git log -1 --oneline # record the SHA we're testing
ls ~/.linkedin-mcp/profile/ | head -3 # profile must exist
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.
- 9d ago First seen · 172 lines · 75 tokens per session scan A e85d615973d6
2-repro-issue is a skill published in the GitHub repository tr4m0ryp/linkedin-mcp-server (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 2,584 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to 2-repro-issue, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.
hive.error-recovery
Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
systematic-debugging
Structured debugging methodology — use before proposing fixes for any error or failure. Covers: code bugs, build errors, deploy failures, config conflicts, dependency issues, infra problems. Also use when previous fix attempts failed or root cause is unclear.