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 skills add ericrisco/rsc-harness --skill linkedin-outreachgit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/linkedin-outreach)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/linkedin-outreach"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/linkedin-outreach/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/ericrisco/rsc-harness/linkedin-outreach"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/linkedin-outreach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00079 | $0.02807 |
| Opus 5 | $0.00039 | $0.01404 |
| Sonnet 5 | $0.00016 | $0.00561 |
| Haiku 4.5 | $0.00008 | $0.00281 |
Grade A, and why
linkedin-outreach 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 8d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linkedin Outreach — The Loop and Its Ledger
You run the LinkedIn social-selling motion and keep its score: who to touch, when, through what warm-up, and how the loop is run and logged. The thesis is warm-first — engagement before connection, signal before send, ledger before "I'll remember it." The output is a running system plus a touch ledger under 02-DOCS/, never a finished line of copy: when prose is needed you write the brief and hand it off, then stay in the loop.
Boundary
The sharpest line is against ../cold-outreach/SKILL.md, and it splits on message-vs-system:
- A single message — the connection note (≤300 chars), the DM bump, its wording and per-inbox send cadence → cold-outreach. If the ask is "write this" or "fix this template," it is not yours.
- The system — who to touch, when, the warm-up, the budget, the ledger → here. When both are in play, this skill drives and delegates the copy.
Also not yours: sourcing / scoring the raw prospect list and ICP definition → ../lead-gen/SKILL.md; the deal after a reply, i.e. stages, forecast, CRM tasks → ../sales-pipeline/SKILL.md; writing or scheduling LinkedIn posts → ../linkedin-content/SKILL.md; brand growth and positioning → ../linkedin-strategy/SKILL.md.
The loop
Five phases, in order. Each has a why and yields one artifact; the artifact gates the next phase. Skipping a phase is how acceptance collapses.
- Target — why: outreach timed to a reason beats outreach timed to a calendar. → Yields a Sales Nav saved search + trigger alerts (job change, funding, recent post).
- Warm — why: a cold, context-free request is the worst-accepting move you can make; engaging first is what fixes it. → Yields a logged pre-touch (profile view + one genuine comment/like 1–2 days prior).
- Connect — why: the request is the smallest, most rate-limited move; spend it deliberately. → Yields a sent request inside the weekly budget, note-or-no-note chosen by goal.
- Convert — why: an accept is not a conversation; the choreography turns a signal into a warm 1:1. → Yields a thread with a real reply, copy delegated to cold-outreach when needed.
- Log — why: a motion you can't measure you can't repeat or fix. → Yields a row in the
02-DOCS/ledger with the outcome.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 155 lines · 79 tokens per session scan A ac85603a0516
linkedin-outreach is a skill published in the GitHub repository ericrisco/rsc-harness (82 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 2,807 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
building-automated-malware-submission-pipeline
Builds an automated malware submission and analysis pipeline that collects suspicious files from endpoints and email gateways, submits them to sandbox environments and multi-engine scanners, and generates verdicts with IOCs for SIEM integration. Use when SOC teams need to scale malware analysis beyond manual sandbox…
merge-aliases
Folds two surface names for the same backend system into one canonical entity, keeping every original mention individually retrievable, and refuses to merge pairs that only share spelling.
anchor-and-lock
Consults a check that sits outside the loop system before finalizing any decision the frozen facts bear on, and refuses every attempt by a loop to rewrite a node marked frozen, regardless of how convergent the loop's own reasoning looks.
query-graph
Loads schema.sql into a local SQLite file, then answers availability and provenance questions against the nodes/edges tables with real SQL instead of re-reading source material.
build-subgraph
Traverses a full graph and returns a bounded subgraph around one target node -- its depth-bounded dependencies plus any disputed claims attached to it -- while proving everything else was left out.
arbitrate-collision
Detects when two loops have proposed conflicting writes to the same node and field at close to the same time, applies a stated priority rule to accept exactly one, and records the rejected write with the reason it lost.