OpenGSC: Skill for Claude Code

.agents/skills/link-prospecting/SKILL.md

link-prospecting is a skill for Claude Code, Codex from fenjo26/OpenGSC. It costs 42 tokens per session (467 once invoked), scanned A, original, MIT.

A skill for finding websites that may be willing to link to your content by examining competitor backlink mentions. A backlink is a link from another website to your site.

In plain words
What is it for?
Use it to find domains linking to multiple competitors, understand which content earns links in a niche, and check the status of your own curated backlinks.
Why use it?
It turns competitor link data into a shortlist of outreach prospects and can also identify dead links on your own site that may be worth reclaiming.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is fenjo26/OpenGSC's own configuration. It tells Claude Code and Codex how to work on OpenGSC 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 OpenGSC configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fenjo26/OpenGSC. 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/fenjo26/OpenGSC/main/.agents/skills/link-prospecting/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fenjo26/OpenGSC

Made for: Claude Code, Codex.

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 link-prospecting

README.md
[![agentmods](https://agentmods.dev/badge/skills/fenjo26/opengsc/link-prospecting.svg)](https://agentmods.dev/skills/fenjo26/opengsc/link-prospecting)
Your own site
<a href="https://agentmods.dev/skills/fenjo26/opengsc/link-prospecting"><img src="https://agentmods.dev/badge/skills/fenjo26/opengsc/link-prospecting.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 467 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 $0.00042 $0.00467
Opus 5 $0.00021 $0.00234
Sonnet 5 $0.00008 $0.00093
Haiku 4.5 $0.00004 $0.00047

Measured 8d ago against content hash e463d011da04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

link-prospecting 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.

.agents/skills/link-prospecting/SKILL.md · 40 lines

What it actually says

Goal

Produce a concrete outreach shortlist: which domains to contact, why they're likely to link, and what content to pitch — grounded in the fresh competitor backlinks the user's Link Monitor has already pulled from Ahrefs.

Required inputs

  • Optional: a specific watched brand to focus on, and the user's own site for the backlink-health check.

OpenGSC MCP tools

  • get_link_mentions: fresh quality backlinks earned by the watched competitor brands + multiLinkerDomains (domains linking to 2+ brands — the highest-probability outreach targets). This is the core tool.
  • get_backlinks: the user's OWN curated backlink inventory with liveness/indexed status — use to spot dead links worth reclaiming.
  • list_sites: resolve the user's site if backlink health is in scope.

Workflow

  1. Call get_link_mentions. If it returns a "no data yet" note, stop and tell the user to add brands and run a pull under SEO Tools → Link Monitor.
  2. Prioritize multiLinkerDomains: a domain that linked to two competitors but not the user is the warmest lead.
  3. From mentions, infer WHAT earns links in this niche: content types (studies, comparisons, tools), anchor patterns, and the context titles suggest.
  4. If the user's site is known, call get_backlinks and list dead (alive: false) links as reclamation targets — the cheapest wins in link building.
  5. Build the outreach shortlist with a specific pitch angle per domain.

Output format

  • Top 5 outreach targets: domain, DR (from data), which brands it linked, suggested pitch.
  • Content/PR ideas the mention data supports (with example source titles as evidence).
  • Reclamation list (dead backlinks), if any.

Guardrails

  • Do not fabricate DR values or mentions; every claim must trace to a returned row.
  • Never suggest paid links or PBNs; keep recommendations white-hat outreach/content.
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. 8d ago First seen · 40 lines · 42 tokens per session scan A e463d011da04

Subscribe to this mod's changes

link-prospecting is a skill published in the GitHub repository fenjo26/OpenGSC (20 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 467 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

reskin

Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…

CopilotKit/CopilotKit · 154 tokens

copilotkit-setup

Use when adding CopilotKit to an existing project or bootstrapping a new CopilotKit project from scratch. Covers framework detection, package installation, runtime wiring (managed Intelligence or self-hosted SSE), provider setup, and first working chat integration.

CopilotKit/CopilotKit · 56 tokens

setup-slack-channel

Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…

CopilotKit/CopilotKit · 206 tokens

copilotkit-channels

Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…

CopilotKit/CopilotKit · 112 tokens

runtime

@copilotkit/runtime — mount a fetch-native CopilotRuntime on any JS server, wire middleware, pick an AgentRunner, instantiate BuiltInAgent (Factory Mode with TanStack AI is the preferred default) or plug in any of 12 external agent frameworks (Mastra, LangGraph, CrewAI Crews/Flows, PydanticAI, ADK, LlamaIndex, Agno…

CopilotKit/CopilotKit · 150 tokens

a2ui-renderer

Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…

CopilotKit/CopilotKit · 175 tokens