codex-profiles: Skill for Codex

.agents/skills/github-monitoring/SKILL.md

github-monitoring is a skill for Codex from Ducksss/codex-profiles. It costs 46 tokens per session (1,129 once invoked), scanned A, original, MIT.

A monitoring procedure for existing GitHub outreach work, such as pull requests, issues, and listings. It also reconciles those records with Airtable, a cloud database used to track the work.

In plain words
What is it for?
Rechecking GitHub links and statuses, updating Airtable targets, and recording follow-up activity without creating new outreach.
Why use it?
It prevents outreach records from becoming outdated or inconsistent. It clarifies what happened after a submission or review and what should happen next.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is Ducksss/codex-profiles's own configuration. It tells Codex how to work on codex-profiles 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 codex-profiles configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/outreach-tracker.mjs list --status "Issue Open" --json.

Reuse

Borrowing it

Nothing to install: this file belongs to Ducksss/codex-profiles. 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/Ducksss/codex-profiles/main/.agents/skills/github-monitoring/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Ducksss/codex-profiles

Made for: 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 github-monitoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/ducksss/codex-profiles/github-monitoring.svg)](https://agentmods.dev/skills/ducksss/codex-profiles/github-monitoring)
Your own site
<a href="https://agentmods.dev/skills/ducksss/codex-profiles/github-monitoring"><img src="https://agentmods.dev/badge/skills/ducksss/codex-profiles/github-monitoring.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,129 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 $0.00046 $0.01129
Opus 5 $0.00023 $0.00564
Sonnet 5 $0.00009 $0.00226
Haiku 4.5 $0.00005 $0.00113

Measured yesterday against content hash d7f6cce1e24d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

github-monitoring 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 yesterday.

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-monitoring/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Monitoring

Purpose

Recheck existing GitHub outreach work, reconcile the tracker, and route any new work back to the correct phase. This skill does not create leads or drafts.

Required Context

Read policy gates in ops/outreach/launch.md, the live tracker target, and the existing PR, issue, listing, or submission URL. Load references/status-map.md before updating status.

Boundaries

  • Recheck existing PRs, issues, listings, and tracker target links.
  • Update tracker Targets and append Log entries only.
  • Use Log.Workflow = monitoring for every meaningful recheck.
  • Do not discover new leads.
  • Do not draft PRs, issues, comments, emails, DMs, forum posts, listing submissions, or maintainer replies.
  • Do not submit, open, post, comment, email, DM, or otherwise contact externally.

Accepted Input

  • Consume targets in Issue Open, PR Open, or Pending Review with a recorded external URL and a dated recheck due in Next Action.
  • Also consume recheckable Deferred targets and Listed targets due for link verification. A missing or inaccessible external URL is a repair input when the target or its history identifies the external work; it is not grounds to replace or delete the platform record.
  • Monitoring may route to Run closing draft or Run lead qualification, but it never performs those phases itself.

Tracker Protocol

Create a unique run-<UTC-timestamp>-<random-suffix> <run-id> and list each accepted status independently. Inspect the external state read-only, then claim the target immediately before writing reconciliation results:

node scripts/outreach-tracker.mjs list --status "Issue Open" --json
node scripts/outreach-tracker.mjs list --status "PR Open" --json
node scripts/outreach-tracker.mjs list --status "Pending Review" --json
node scripts/outreach-tracker.mjs list --status Deferred --json
node scripts/outreach-tracker.mjs list --status Listed --json
node scripts/outreach-tracker.mjs get <key> --json
node scripts/outreach-tracker.mjs claim <key> --by <run-id>

Read the full file on GitHub · 106 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.

  1. yesterday Changed d7f6cce1e24d
  2. 2d ago Changed de637a5a8134
  3. 7d ago First seen · 106 lines · 46 tokens per session scan A 42f2bbf707a4

Subscribe to this mod's changes

github-monitoring is a skill published in the GitHub repository Ducksss/codex-profiles (117 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 1,129 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.