Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wrg32786/aigent-osnpx agentmods add skills/wrg32786/aigent-os/codex-adapterWrote 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/wrg32786/aigent-os/codex-adapter)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/codex-adapter"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/codex-adapter/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/wrg32786/aigent-os/codex-adapter"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/codex-adapter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00101 | $0.00882 |
| Opus 5.5 | $0.00040 | $0.00353 |
| Sonnet 5.5 | $0.00020 | $0.00176 |
| Haiku 4.5 | $0.00010 | $0.00088 |
Grade A, and why
codex-adapter 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Adapter
This is aigent-OS's first (and currently only) non-Claude executor: a thin wrapper around daemons/codex-adapter.sh that runs a single bounded, mechanical task through the Codex CLI's non-interactive codex exec mode.
Scope -- what "bounded and mechanical" means
Good fits: a scripted rename, a config/gitignore entry, a repetitive multi-file edit with a clear before/after, a lint-fix pass. The task prompt you hand it should be checkable by a human (or you) glancing at the resulting diff -- if you can't describe in one sentence what "done" looks like, it's not bounded enough for this adapter; do it yourself instead.
Not a fit: architecture decisions, anything requiring judgment about tradeoffs, anything touching credentials/secrets/production config, anything the user hasn't explicitly asked to route to Codex.
Before you invoke it
- Confirm the Codex CLI is actually available:
command -v codex(or whateverAIGENT_CODEX_BINis set to). If it isn't installed, tell the user instead of guessing at a path. - State the bounded task in one sentence, and the target directory. If either is unclear, ask -- don't invoke on a guess.
Invocation
bash daemons/codex-adapter.sh "<bounded task prompt>" --dir <path> [--sandbox <mode>]
AIGENT_CODEX_BIN(env, defaultcodex) -- path or name of the Codex CLI binary. Never hardcode a machine-specific path in the invocation; set the env var if the binary isn't onPATH.--dir <path>-- working directory the task runs in. Default: current directory.--sandbox <mode>-- passed through tocodex exec --sandbox. Defaultworkspace-write(Codex may read/write inside--dir, nothing wider).
Example:
AIGENT_CODEX_BIN=codex bash daemons/codex-adapter.sh \
"Add a .gitignore entry for *.tmp files" --dir .
After it runs -- the review gate
The adapter never commits or pushes. It writes:
.aigent/codex-runs/<timestamp>/output.log-- the raw Codex CLI transcript.aigent/codex-runs/<timestamp>/review.diff-- a working-tree diff (tracked changes + a synthetic diff for any new untracked files) if--diris a git repository.aigent/codex-runs/<timestamp>/status.txt--git status --porcelainfor the same tree
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.
- 1mo ago First seen · 60 lines · 101 tokens per session scan A d5478869faf6
codex-adapter is a skill published in the GitHub repository wrg32786/aigent-os (24 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 882 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-01.
Other skills, from other repositories
git-commit
A guided Git commit workflow that examines changes and creates a commit message using the Conventional Commits format, a shared style for labeling changes such as features, fixes, tests, or documentation.
meeting-todos
Use when the user says /meeting-todos, "the meeting is done", "I just had a meeting", "pull the action items", "what did I commit to", or otherwise wants action items from a recent meeting note captured on their to-do list. Also when a meeting note or transcript needs its tasks pulled out. NOT for general task…
instinct-import
Use when bringing a teammate's, another machine's, or another harness's instincts into this vault: the user runs /instinct-import, shares a portable YAML instinct pack (PACK.yaml), or asks to merge, adopt, sync, or inherit shared instincts. Confidence-gated so local instincts are never clobbered. Part of the Instinct…
secret-warn
Use when adding or tuning edit-time secret and code-injection guardrails or security hooks in Claude Code, or on mentions of secret detection, API key safety, hardcoded or leaked keys (AWS, Stripe, GCP, OpenAI, Anthropic, GitHub, Slack, JWT, PEM, .env), gitleaks-style or pre-commit secret scanning, false positives or…
commit-helper
Conventional commit helper — analyze changes, detect secrets, create well-formatted commit.
doubt-driven-development
Use when correctness matters more than speed: about to commit non-trivial code, make an architectural call under uncertainty, work in unfamiliar code, or assert what the compiler cannot check ('this is safe', 'thread-safe', 'this scales', 'matches the spec'). Strongest on high-stakes surfaces (production deploys…