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.
git clone --depth 1 https://github.com/Arystos/skill-codexWrote 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/commands/arystos/skill-codex/codex-do)<a href="https://agentmods.dev/commands/arystos/skill-codex/codex-do"><img src="https://agentmods.dev/badge/commands/arystos/skill-codex/codex-do/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/arystos/skill-codex/codex-do"><img src="https://agentmods.dev/badge/commands/arystos/skill-codex/codex-do.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00020 | $0.01300 |
| Opus 5.5 | $0.00008 | $0.00520 |
| Sonnet 5.5 | $0.00004 | $0.00260 |
| Haiku 4.5 | $0.00002 | $0.00130 |
Grade B, and why
codex-do scanned grade B with 1 finding 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 12d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **`--effort` omitted:** do NOT pass `reasoningEffort`. Codex uses its configured default (`~/.codex/config.toml`). How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegate Task to Codex
Delegate a well-scoped implementation task to Codex. Codex may touch only an agreed list of files, and the task is done only when a verification command passes.
Instructions
You are delegating an implementation task to Codex. Follow these steps:
-
Extract optional flags from
$ARGUMENTSfirst, then treat the remaining text as the task:--effort <level>— Codex reasoning effort. Valid:minimal,low,medium,high,xhigh. If an invalid level is given, list the valid ones and ask — do not guess.--model <name>— Codex model. Passed through as-is; an explicit--modelalways wins.- Strip any flags you find; what's left is the task parsed in step 1.
--effortomitted: do NOT passreasoningEffort. Codex uses its configured default (~/.codex/config.toml).--modelomitted: choose the model yourself from the list in thecodex_exectool'smodelparameter (only those slugs exist on this account). Match the task: the strongest listed model for multi-file or tricky work, a fast one for small mechanical edits. If no list is shown or you are unsure, omitmodelso Codex uses the user's default. If Codex rejects the model, the call falls back to the default on its own.
-
Parse the task from
$ARGUMENTS. If the argument is vague or missing, ask the user to be more specific before proceeding. -
Evaluate if the task is suitable for delegation:
- Good for Codex: repetitive bulk changes, boilerplate generation, test writing for existing code, migration scripts, file format conversions, well-defined single-file edits
- Keep for yourself: architectural decisions, cross-module refactoring, tasks requiring deep conversation context, ambiguous requirements, and trivial edits you'd finish faster yourself than you can write a spec for
- Requires git. Run
git rev-parse --is-inside-work-tree. Delegation needs git to detect every changed file. In a project without git (e.g. Diversion), do not delegate: say so and offer to do the task yourself. - If the task is poorly scoped, explain why and suggest how to break it down.
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.
- 12d ago Changed · +23 lines · +20 tokens per session scan A → B 84288bc43e4f
- 2mo ago First seen · 46 lines · 0 tokens per session scan A b4076627732e
codex-do is a command published in the GitHub repository Arystos/skill-codex (7 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 1,300 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
review-code
Trigger a comprehensive code review on recent changes or specified files.
deslop
Audit a standing codebase for accumulated slop — comment noise, AI-tell doc prose, speculative abstraction, reinvented stdlib, duplicate helpers, dead code, swallowed errors, convention drift. Fans out read-only auditors sharded by wiki domain and writes an indexed report into a scratchpad for you to read. /deslop…
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
implement
Implement in the main agent, with atomic-reviewer gating every checkpoint. For work whose context is already in this conversation, where a fresh subagent would have to re-read what you have already read. Same checkpoints, commit-per-green, and finalize as /subagent-implementation; you write the code.