What is github-lead-gen?

A workflow for finding possible software-project leads on GitHub and recording them in Airtable, a shared online database.

Use it to search for repository candidates, check them against existing Airtable targets, create or update shallow intake records, and hand accepted candidates to a later qualification step.

It keeps candidate discovery separate from qualification and outreach, while preventing duplicate records. It also preserves a brief reason for accepting each candidate.

github-lead-gen — Skill by Ducksss

Install

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.

agentmods

npx agentmods add skills/ducksss/codex-profiles/github-lead-gen

Any agent

npx skills add Ducksss/codex-profiles --skill github-lead-gen

Clone the repo

git clone --depth 1 https://github.com/Ducksss/codex-profiles

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 938 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00040	$0.00938
Opus 5	$0.00020	$0.00469
Sonnet 5	$0.00008	$0.00188
Haiku 4.5	$0.00004	$0.00094

Measured 2d ago against content hash 7e5675e1bb53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-lead-gen 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 2d 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/github-lead-gen/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Lead Gen

Purpose

Find GitHub repository candidates for codex-profiles, dedupe them against Airtable, and hand them off for later qualification. This skill only handles candidate discovery and shallow intake.

Required Context

Before searching, read current product positioning from README.md, policy gates from LAUNCH.md, and live distribution state from the Airtable tracker. Load references/search-patterns.md for approved search lanes and example queries.

Boundaries

Create or update Airtable Targets only.
Dedupe against existing Airtable targets before creating records.
Use Log.Workflow = github-lead-gen for every meaningful intake decision.
Set Next Action = Run lead qualification on every accepted candidate.
Record only a shallow candidate reason; do not assign final ICP.
Do not draft PRs, issues, comments, emails, DMs, forum posts, or listing submissions.
Do not contact externally.
Do not change LAUNCH.md unless the user explicitly asks for a repo-local handoff.

Accepted Input

A new repository candidate with no matching Airtable target, or an existing target that needs shallow lead-generation evidence refreshed.
Do not overwrite a qualified or submitted target's Status, ICP decision, or phase-specific Next Action.
Every accepted new target leaves this phase as Status = Backlog and Next Action = Run lead qualification.

Tracker Protocol

Create one unique run-<UTC-timestamp>-<random-suffix> value and use it as <run-id> for the whole invocation. Start with the complete ledger:

node scripts/outreach-tracker.mjs list --json

For an existing target, claim it before changing fields. For a new target, atomically create the shallow row first, then claim it before adding evidence or logging the handoff:

node scripts/outreach-tracker.mjs upsert <key> --name "<name>" \
  --channel "<channel>" --status Backlog \
  --next-action "Run lead qualification" --notes "<candidate reason and source>"
node scripts/outreach-tracker.mjs claim <key> --by <run-id>

Read the full file on GitHub · 104 lines

Files

What ships with it

2 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.

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.

2d ago First seen · 104 lines · 40 tokens per session scan A 7e5675e1bb53

Subscribe to this mod's changes

github-lead-gen is a skill published in the GitHub repository Ducksss/codex-profiles (108 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 938 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.

Databases Productivity Research bash cli codex developer-tools macos openai

claude-api

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…

warpdotdev/warp · 193 tokens

create-skill

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

warpdotdev/warp · 64 tokens

contacts

Manage contacts, communication channels, access control, and invite links.

vellum-ai/vellum-assistant · 14 tokens

gmail

Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.

vellum-ai/vellum-assistant · 20 tokens

gui-integration-test

GUI desktop app only. Writes, runs, and debugs Warp integration tests using the custom Builder/TestStep framework in crates/integration. Use when adding a new integration test, fixing a failing integration test, wiring a test into the manual runner or nextest suite, or verifying end-to-end UI and terminal behavior in…

warpdotdev/warp · 72 tokens

gui-onboarding-verification-skill

GUI desktop app only. Launch two parallel Oz cloud agents with computer use to download and install the latest stable Linux Warp build, capture screenshots while walking through first-time onboarding in both logged-out and logged-in states, then selectively fan out follow-up cloud agents for distinct onboarding…

warpdotdev/warp · 98 tokens