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 skills add drippy-passport968/agent-supervision-skills --skill codex-supervisiongit clone --depth 1 https://github.com/drippy-passport968/agent-supervision-skillsWrote 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/drippy-passport968/agent-supervision-skills/codex-supervision)<a href="https://agentmods.dev/skills/drippy-passport968/agent-supervision-skills/codex-supervision"><img src="https://agentmods.dev/badge/skills/drippy-passport968/agent-supervision-skills/codex-supervision/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/skills/drippy-passport968/agent-supervision-skills/codex-supervision"><img src="https://agentmods.dev/badge/skills/drippy-passport968/agent-supervision-skills/codex-supervision.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 | $0.00067 | $0.05193 |
| Opus 5 | $0.00034 | $0.02596 |
| Sonnet 5 | $0.00013 | $0.01039 |
| Haiku 4.5 | $0.00007 | $0.00519 |
Grade A, and why
codex-supervision scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- codex-supervision — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Supervision
Hand work to the local codex CLI and supervise the result — read what Codex actually did, inspect artifacts, verify claims, only then answer the user.
Supervision, not blind delegation.
This skill exists because the official openai/codex-plugin-cc is a Claude Code plugin, and Claude Desktop (consumer chat client) does not load plugins. The skill provides the essential capability via PowerShell wrapper scripts the model invokes through its shell tool.
Requirements
- PowerShell 7+ (
pwsh.exe). UsesProcessStartInfo.ArgumentListandProcess.Kill(bool)which are .NET Core 3+ only — Windows PowerShell 5.1 will not work.codex-setup.ps1reports the detected version and refuses to markready=trueon older hosts. - Node.js 18.18+ (codex CLI requirement)
codexCLI 0.128+ on PATH, at$env:CODEX_PATH, or at%USERPROFILE%\bin\codex.cmd- A ChatGPT subscription or OpenAI API key for codex authentication
What this skill provides
PowerShell scripts under scripts/:
common.ps1— codex resolution, env hygiene, async I/O, timeout, artifact capturecodex-setup.ps1— verify codex CLI version + login + writable state dircodex-review.ps1— non-interactive code review (normal or adversarial) viacodex exec reviewcodex-task.ps1— delegate an arbitrary task to codex (rescue equivalent)codex-list-sessions.ps1— inspect prior runs
These scripts:
- require a locally installed
codexCLI on PATH, at$env:CODEX_PATH, or at%USERPROFILE%\bin\codex.cmd - read/write UTF-8; set
Console.OutputEncodingto UTF-8 to survive Chinese-locale Windows - run codex non-interactively (
codex exec/codex exec review) with async stdout/stderr reads — no pipe-buffer deadlock - enforce a
-TimeoutSecand kill codex if it hangs - pass
-Base/-Uncommitted/-Titlethrough to the native review subcommand (codex does the git diff scoping itself) - default to
read-onlysandbox; only escalate toworkspace-writewith-Write, ordanger-full-accesswith-DangerousFullAccess - always write
last-prompt.txt,last-response.txt,stderr.log,session.jsonto the session dir
What ships with it
5 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.
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 First seen · 392 lines · 67 tokens per session scan A 659c6ef68e66
codex-supervision is a skill published in the GitHub repository drippy-passport968/agent-supervision-skills (3 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 5,193 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
security-review
Complete a security review of the pending changes on the current branch.
code-review
Review the current diff, or a PR number/branch/path target, for correctness bugs and reuse/simplification/efficiency cleanups at the given effort level (low/medium: fewer, high-confidence findings; high→max: broader coverage, may include uncertain findings; ultra: deep multi-agent review in the cloud); with no level…
contribute-to-eliza
Finish and prove a scoped elizaOS GitHub issue, or independently review and repair an open elizaOS pull request. Use when contributing compute to elizaOS by selecting unclaimed work, implementing or reviewing changes, adding real tests and evidence, validating artifacts, or preparing a contribution for maintainer…
simplify
Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.
ha-code-review
Hope-native review of uncommitted, staged, commit, branch, or PR changes: discover concrete regressions, independently verify candidates, and report actionable findings first without speculative noise.
factory-rereview
Re-review a pull request after a push — reconcile the previous review against the new commits, look for new defects the push introduced, then a fresh pass over the whole PR, and finish with a verdict on the PR.