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 skills/mikemanifold/codex-unified/codex-bugnpx skills add MikeManifold/codex-unified --skill codex-buggit clone --depth 1 https://github.com/MikeManifold/codex-unifiedWrote 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.
[](https://agentmods.dev/skills/mikemanifold/codex-unified/codex-bug)<a href="https://agentmods.dev/skills/mikemanifold/codex-unified/codex-bug"><img src="https://agentmods.dev/badge/skills/mikemanifold/codex-unified/codex-bug.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00066 | $0.00562 |
| Opus 5 | $0.00033 | $0.00281 |
| Sonnet 5 | $0.00013 | $0.00112 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
codex-bug 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 3d 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.
This is a copy
100% identical to codex-bug — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Bug
Overview
Diagnose a Codex GitHub bug report and decide the next action: verify against sources, request more info, or explain why it is not a bug.
Workflow
- Confirm the input
- Require a GitHub issue URL that points to
github.com/openai/codex/issues/…. - If the URL is missing or not in the right repo, ask the user for the correct link.
- Network access
- Always access the issue over the network immediately, even if you think access is blocked or unavailable.
- Prefer the GitHub API over HTML pages because the HTML is noisy:
- Issue:
https://api.github.com/repos/openai/codex/issues/<number> - Comments:
https://api.github.com/repos/openai/codex/issues/<number>/comments
- Issue:
- If the environment requires explicit approval, request it on demand via the tool and continue without additional user prompting.
- Only if the network attempt fails after requesting approval, explain what you can do offline (e.g., draft a response template) and ask how to proceed.
- Read the issue
- Use the GitHub API responses (issue + comments) as the source of truth rather than scraping the HTML issue page.
- Extract: title, body, repro steps, expected vs actual, environment, logs, and any attachments.
- Note whether the report already includes logs or session details.
- If the report includes a thread ID, mention it in the summary and use it to look up the logs and session details if you have access to them.
- Summarize the bug before investigating
- Before inspecting code, docs, or logs in depth, write a short summary of the report in your own words.
- Include the reported behavior, expected behavior, repro steps, environment, and what evidence is already attached or missing.
- Decide the course of action
- Verify with sources when the report is specific and likely reproducible. Inspect relevant Codex files (or mention the files to inspect if access is unavailable).
- Request more information when the report is vague, missing repro steps, or lacks logs/environment.
- Explain not a bug when the report contradicts current behavior or documented constraints (cite the evidence from the issue and any local sources you checked).
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.
- 3d ago First seen · 49 lines · 66 tokens per session scan A cfdaae2defa5
codex-bug is a skill published in the GitHub repository MikeManifold/codex-unified (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 66 tokens to every session and 562 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to codex-bug, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
image-generation
Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.
connect-agent
Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
agent-improve
Turns production evidence into tested improvements for your AI agent. Forms hypotheses from real traces and analytics, explains the reasoning behind each one, then executes with the user: scenario tests that reproduce production failures, prompt and code changes as reviewable PRs, new evaluators and monitors that…
feature-map
Maintain the canonical LangWatch feature map (/feature-map.json). Use when adding features, APIs, MCP tools, CLI commands, or skills — to update the central registry and keep surfaces in sync.