codex

codex is a skill for Claude Code, Codex from V-Songbird/slag. It costs 189 tokens per session (5,525 once invoked), scanned A, a copy of assay, MIT.

An audit tool for Codex project instructions, including AGENTS.md files, listed skills, and related hooks. It reports instructions that Codex cannot use because they are hidden, too large, missing, or contradictory.

In plain words
What is it for?
Use it to inspect the instruction chain Codex loads and find inactive, conflicting, or unreachable guidance.
Why use it?
It helps explain why an instruction appears to have no effect without changing the project's files.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the assay plugin — 9 skills shipped together

Install

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.

agentmods
npx agentmods add skills/v-songbird/slag/codex
Any agent
npx skills add V-Songbird/slag --skill codex
Clone the repo
git clone --depth 1 https://github.com/V-Songbird/slag

Made for: Claude Code, Codex.

Or install assay, the plugin that ships this one along with the rest of its 9 skills.

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 codex

README.md
[![agentmods](https://agentmods.dev/badge/skills/v-songbird/slag/codex.svg)](https://agentmods.dev/skills/v-songbird/slag/codex)
Your own site
<a href="https://agentmods.dev/skills/v-songbird/slag/codex"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/codex.svg" alt="Measured on agentmods" height="20"></a>
Per session 189 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,525 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 88% copy Near-identical to another mod 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 $0.00189 $0.05525
Opus 5 $0.00095 $0.02763
Sonnet 5 $0.00038 $0.01105
Haiku 4.5 $0.00019 $0.00553

Measured 3d ago against content hash 3e7613a61969, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

Origin

This is a copy

88% identical to assay — 330 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.

assay/skills/codex/SKILL.md · 405 lines

How it starts

The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.

assay:codex

Every assay.js call that reads or writes the project's instruction files carries --host codex only where it runs discovery — scan, remeasure, ci and validate. Every other command reads the host off the saved records and refuses the flag outright. The profile decides which files are sources, which analyses apply, and what validate checks, so pass it wherever it is taken and nowhere else. rollback and clean work off the journal and take no host.

--startup <path> belongs to this skill: Codex reads the chain from the project root down to the directory the session began in, so auditing a session that starts in a subdirectory needs that directory named. Pass it to scan alongside --host codex when $ARGUMENTS carries it — the scan fixes it in the saved context report reads. The commands that re-scan inherit nothing from that context: remeasure and validate need --host codex and the same --startup passed again.

Other flags in $ARGUMENTS: --dry-run (audit and preview only — the menu is not asked, nothing is written), --verbose (the full report), --json (the machine-readable record), --top <n> (show more than the default 8 rows in the fix table), --no-verify (skip the subagent in step 2, which otherwise runs), --deterministic (skip every model step), --semantic (also propose duplicates and conflicts the script cannot see), --project-only (skip the user's own instruction files).

What this profile does not do. There is no letter grade and no wording score here: the structural-hygiene weights were measured against one host's prose and carry no evidence for this one. Skills are checked against the metadata Codex documents as required — name, description, the agents/openai.yaml sidecar, duplicate names, the collective listing budget — not against the trigger recipe, which was measured against a different router. Say that plainly rather than implying anything here was scored.

1. Scan

From the project root:

Read the full file on GitHub · 405 lines

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. 3d ago First seen · 405 lines · 189 tokens per session scan A 3e7613a61969

Subscribe to this mod's changes

codex is a skill published in the GitHub repository V-Songbird/slag (2 stars, last pushed 5d ago), licensed MIT. It adds 189 tokens to every session and 5,525 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to assay, differing in 330 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens