MCP-Linkedin: Skill for Claude Code

.agents/skills/3-verify-pr-fix/SKILL.md

3-verify-pr-fix is a skill for Claude Code from kaistenberg/MCP-Linkedin. It costs 77 tokens per session (3,409 once invoked), scanned A, a copy of 3-verify-pr-fix, Apache-2.0.

A read-only workflow for checking whether a proposed GitHub pull request actually fixes a reported problem. It runs the same request before and after the change, then reviews the implementation.

In plain words
What is it for?
It is for testing a candidate pull request on the LinkedIn MCP server, comparing its output with a baseline, and checking locale independence, stable page handling, and change scope. A pull request is a proposed code change.
Why use it?
It provides a repeatable way to distinguish a working fix from a change that only appears to solve the issue.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md; positional $N argument; installed under .agents/ (shared by several agents).

This is kaistenberg/MCP-Linkedin's own configuration. It tells Claude Code how to work on MCP-Linkedin itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MCP-Linkedin configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kaistenberg/MCP-Linkedin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kaistenberg/MCP-Linkedin/main/.agents/skills/3-verify-pr-fix/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kaistenberg/MCP-Linkedin

Made for: Claude Code.

Wrote 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.

agentmods badge for 3-verify-pr-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/kaistenberg/mcp-linkedin/3-verify-pr-fix/github.svg)](https://agentmods.dev/skills/kaistenberg/mcp-linkedin/3-verify-pr-fix)
Your own site
<a href="https://agentmods.dev/skills/kaistenberg/mcp-linkedin/3-verify-pr-fix"><img src="https://agentmods.dev/badge/skills/kaistenberg/mcp-linkedin/3-verify-pr-fix/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.

agentmods 80×15 button for 3-verify-pr-fix

Your own site · 80×15
<a href="https://agentmods.dev/skills/kaistenberg/mcp-linkedin/3-verify-pr-fix"><img src="https://agentmods.dev/badge/skills/kaistenberg/mcp-linkedin/3-verify-pr-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,409 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.03409
Opus 5 $0.00039 $0.01705
Sonnet 5 $0.00015 $0.00682
Haiku 4.5 $0.00008 $0.00341

Measured 9d ago against content hash 156cac8c102f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

3-verify-pr-fix 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/verify-pr-$PR-headers -X POST http://127.0.0.1:$PORT/mcp \
Origin

This is a copy

100% identical to 3-verify-pr-fix — 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.

.agents/skills/3-verify-pr-fix/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify a Candidate PR Actually Fixes the Issue

Goal: take a PR number, check it out cleanly, re-run the same tool call that failed on main, compare the outputs, and produce a verdict — "fixes", "fixes but with concerns", "does not fix", or "cannot run". Pair with /2-repro-issue (which produces the baseline). No edits, no merges, no pushes.

Phase 1 — Resolve the PR and its linked issue

# Accept "498", "#498", or "https://github.com/.../pull/498" — extract the digits only
PR=$(echo "$ARGUMENTS" | sed -E 's|.*/||; s|#||g' | grep -oE '^[0-9]+' | head -1)
[ -z "$PR" ] && { echo "Invalid input: '$ARGUMENTS'. Pass a PR number or URL." >&2; exit 1; }
REPO=stickerdaniel/linkedin-mcp-server

gh pr view $PR --repo $REPO --json title,body,baseRefName,headRefName,headRepositoryOwner,mergeable,mergeStateStatus,additions,deletions,changedFiles,maintainerCanModify,statusCheckRollup

Extract the linked issue number from the PR body (Closes #, Fixes #, Resolves #, or plain #N). Call it ISSUE. If multiple, ask the user which one is the verification target.

Phase 2 — Pick up the baseline + request metadata

/2-repro-issue writes two files for each issue:

  • /tmp/repro-issue-<ISSUE>-main.json — the on-main response baseline
  • /tmp/repro-issue-<ISSUE>-meta.json — the {tool, arguments} used to call it

Both must exist. The meta file is how this skill replays the exact same call instead of guessing tool and args from the response body.

ls -la /tmp/repro-issue-$ISSUE-main.json /tmp/repro-issue-$ISSUE-meta.json 2>&1
# Both files must exist AND be non-empty. ls alone never fails the script, so
# guard each path before we touch the PR branch or LinkedIn.
[ -s /tmp/repro-issue-$ISSUE-main.json ] || { echo "Missing or empty response baseline. Re-run /2-repro-issue $ISSUE." >&2; exit 1; }
[ -s /tmp/repro-issue-$ISSUE-meta.json ] || { echo "Missing or empty meta file. Re-run /2-repro-issue $ISSUE." >&2; exit 1; }
TOOL=$(jq -r .tool /tmp/repro-issue-$ISSUE-meta.json)
ARGS_JSON=$(jq -c .arguments /tmp/repro-issue-$ISSUE-meta.json)
echo "Replaying: $TOOL($ARGS_JSON)"

Read the full file on GitHub · 201 lines

Changes

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.

  1. 9d ago First seen · 201 lines · 77 tokens per session scan A 156cac8c102f

Subscribe to this mod's changes

3-verify-pr-fix is a skill published in the GitHub repository kaistenberg/MCP-Linkedin (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 3,409 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 3-verify-pr-fix, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens

write-pr

Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.

tldraw/tldraw · 53 tokens