What is github-closing-draft?

A drafting skill for preparing GitHub pull requests, issues, and other submission text for approved potential contributors found in Airtable, a shared online database. It leaves drafts waiting for human approval and does not send them.

Use it to create target-specific GitHub contribution drafts, record supporting evidence, and set the next action to await approval.

It keeps outreach reviewable and prevents unapproved external contact. It also ensures drafts follow the target repository's contribution rules and recorded qualification status.

github-closing-draft — 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-closing-draft

Any agent

npx skills add Ducksss/codex-profiles --skill github-closing-draft

Clone the repo

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

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 840 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	$0.00046	$0.00840
Opus 5	$0.00023	$0.00420
Sonnet 5	$0.00009	$0.00168
Haiku 4.5	$0.00005	$0.00084

Measured 2d ago against content hash c1ac63fd9448, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-closing-draft 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-closing-draft/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Closing Draft

Purpose

Create target-specific draft artifacts for qualified codex-profiles leads and leave them approval-gated in Airtable. This skill drafts only; it never opens, posts, submits, comments, emails, or sends anything externally.

Required Context

Read README.md, policy gates in LAUNCH.md, the live Airtable target, and the target's contribution rules or submission guidelines. Load references/draft-rules.md before writing copy.

Boundaries

Consume only Airtable targets with ICP: yes.
Use Log.Workflow = closing for every meaningful draft decision.
Update Airtable with the draft, evidence, and approval blocker.
Set Next Action = Await approval to submit draft after a draft is ready.
Follow the target repository's conventions over codex-profiles conventions.
Do not perform lead discovery.
Do not qualify ICP: maybe or ICP: no targets; route unclear fit back to lead qualification.
Do not submit, open, post, comment, email, DM, or otherwise contact externally.

Accepted Input

Consume only Status = Backlog targets with ICP: yes recorded in Notes and Next Action = Run closing draft.
Never draft for ICP: maybe, ICP: no, Deferred, Declined, or Dead targets; route unclear evidence back to lead qualification.

Tracker Protocol

Create a unique run-<UTC-timestamp>-<random-suffix> <run-id>, select the eligible target, inspect it, and acquire its lease before drafting:

node scripts/outreach-tracker.mjs list --status Backlog --json
node scripts/outreach-tracker.mjs get <key> --json
node scripts/outreach-tracker.mjs claim <key> --by <run-id>

If claim exits 3, skip the target without writing or contacting externally. Store the draft or its repo-local path in Notes, hold it for approval, log the stable phase label, and always release:

node scripts/outreach-tracker.mjs upsert <key> \
  --next-action "Await approval to submit draft" \
  --notes "<draft text or repo-local artifact path plus evidence>"
node scripts/outreach-tracker.mjs log --target <key> \
  --workflow closing --action Rechecked \
  --result "Draft prepared; explicit approval required" --link "<target-url>"
node scripts/outreach-tracker.mjs release <key> --by <run-id>

Read the full file on GitHub · 86 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 · 86 lines · 46 tokens per session scan A c1ac63fd9448

Subscribe to this mod's changes

github-closing-draft is a skill published in the GitHub repository Ducksss/codex-profiles (108 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 840 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 Writing and docs 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

gmail

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

vellum-ai/vellum-assistant · 20 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

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

app-builder

Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…

vellum-ai/vellum-assistant · 162 tokens

contacts

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

vellum-ai/vellum-assistant · 14 tokens