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 agentmods add agents/mdelapenya/coding-skills/codexgit clone --depth 1 https://github.com/mdelapenya/coding-skillsWhat 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 | $0.00000 | $0.00602 |
| Opus 5 | $0.00000 | $0.00301 |
| Sonnet 5 | $0.00000 | $0.00120 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
codex 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAI Codex
Topic file for running pr-reviewer from inside OpenAI Codex (CLI / cloud agent).
Fetch tooling
The skill drives its own fetch. Codex has shell access in its sandboxed workspace and is competent with gh (GitHub) and glab (GitLab).
Network requirement: the skill needs outbound network to clone the PR and run platform commands. If the sandbox is offline (the default for many Codex environments), the user must check out the PR before invoking — or paste the PR context (metadata, commits, diff, linked issues, files) into the task. Codex should refuse to invent data it cannot fetch.
Looping primitive
As of writing, OpenAI Codex CLI does not have a /loop primitive — it is an open feature request (codex#15679; a broader scheduling proposal sits at codex#25466 / codex#8317). The Codex cloud app has Automations for recurring tasks, but those are scheduled outside the CLI session and are coarse-grained, not per-iteration of a review.
Until a real loop primitive ships, use one of:
- Iteration prompt — instruct Codex up front: "Run
/pr-reviewer [<num>]up to 3 times, stopping whenfindings.mdrecordsconverged: true." Codex will sequence the rounds itself. - External driver (Codex CLI) — wrap the CLI in a shell
whileloop that breaks on the convergence marker. Cap with--rounds=N. - Codex Automations (cloud app) — if scheduling is required externally (e.g., a nightly re-review), set up an automation that re-runs the task. Much coarser than per-iteration looping.
--rounds=N is the universal hard stop. Always pass it.
Posting the final report
If outbound network is available:
gh pr review <pr-number> --comment --body-file <path-the-skill-printed>
If the sandbox is offline, print the report and let the user post it themselves. Do not "simulate" posting.
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.
- yesterday First seen · 40 lines · 0 tokens per session scan A 80e9ab43bf22
codex is an agent published in the GitHub repository mdelapenya/coding-skills (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 602 tokens. 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.