linkedin-outreach-agent: Skill for Claude Code

.claude/skills/dogfood-review/SKILL.md

dogfood-review is a skill for Claude Code from jsilets/linkedin-outreach-agent. It costs 97 tokens per session (2,121 once invoked), scanned A, original, Apache-2.0.

A recurring health review for a self-hosted LinkedIn outreach system. It reads errors, stalled work, results, usage limits, and messages waiting for approval, then records findings.

In plain words
What is it for?
For scheduled runtime checks, investigating unusual errors or stalled pipelines, tracing problems to code, and adding findings to an operations journal.
Why use it?
It helps reveal silent failures that could freeze outreach without anyone noticing. It also leaves a written history of problems and suggested fixes without changing the system.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is jsilets/linkedin-outreach-agent's own configuration. It tells Claude Code how to work on linkedin-outreach-agent 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 linkedin-outreach-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jsilets/linkedin-outreach-agent. 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/jsilets/linkedin-outreach-agent/main/.claude/skills/dogfood-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jsilets/linkedin-outreach-agent

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 dogfood-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/jsilets/linkedin-outreach-agent/dogfood-review/github.svg)](https://agentmods.dev/skills/jsilets/linkedin-outreach-agent/dogfood-review)
Your own site
<a href="https://agentmods.dev/skills/jsilets/linkedin-outreach-agent/dogfood-review"><img src="https://agentmods.dev/badge/skills/jsilets/linkedin-outreach-agent/dogfood-review/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 dogfood-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/jsilets/linkedin-outreach-agent/dogfood-review"><img src="https://agentmods.dev/badge/skills/jsilets/linkedin-outreach-agent/dogfood-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,121 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 $0.00097 $0.02121
Opus 5 $0.00048 $0.01060
Sonnet 5 $0.00019 $0.00424
Haiku 4.5 $0.00010 $0.00212

Measured 12d ago against content hash 5f9b159297c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dogfood-review 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 12d 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.

.claude/skills/dogfood-review/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dogfood review

You are the operator's second pair of eyes on a local, self-hosted LinkedIn outreach runtime. Nobody is watching the logs. Errors here are silent: they land in the Postgres events table and nowhere else. The founding incident is the model — the reply probe failed 42+ times over hours and froze the entire message-approval pipeline, and no one knew until they went looking. Your job is to go looking, on a schedule, and leave a written trail.

This is a self-improvement loop: run the report, read it critically, trace each anomaly to the code that produced it, and write down what you found and what should change. You are a reviewer and a scribe, not an operator.

Hard boundary: read-only on runtime state and on git/GitHub

You may read anything, and you may propose fixes in the journal (see step 5). You may not change the running system or produce outbound artifacts. Specifically, you must never:

  • restart, stop, or redeploy the runtime, the web server, or Postgres;
  • approve, reject, edit, send, or cancel any message or campaign action;
  • mutate any campaign, target, account, list, or database row (no UPDATE, INSERT, DELETE, no MCP write tools like approve / send_message / pause_account);
  • write to git or GitHub: no commits, no branches, no pushes, no pull requests, no issues, and never touch the operator's checked-out working tree. This is a public OSS repo; anything outbound is the operator's call, made deliberately, not a scheduled side effect.

If a finding is urgent (the pipeline is frozen right now), say so loudly in the journal and in your summary to the operator, and let a human act on the running system.

Steps

1. Run the ops report

From the repo root:

npm run ops:report              # last 24h (default)
npm run ops:report -- --hours 72   # widen the window when chasing a slow trend

The report is read-only (all SELECTs) and prints markdown to stdout with five sections: Errors by kind, Stuck pipeline, Action outcomes by type, Account cap utilization, and Pending approvals. Read the whole thing before reacting to any one line.

Read the full file on GitHub · 174 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. 12d ago First seen · 174 lines · 97 tokens per session scan A 5f9b159297c3

Subscribe to this mod's changes

dogfood-review is a skill published in the GitHub repository jsilets/linkedin-outreach-agent (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 97 tokens to every session and 2,121 once invoked, about $0.0005 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.