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/boshu2/agentops/codex-execnpx skills add boshu2/agentops --skill codex-execgit clone --depth 1 https://github.com/boshu2/agentopsWhat 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 | $0.00037 | $0.01074 |
| Opus 5 | $0.00018 | $0.00537 |
| Sonnet 5 | $0.00007 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
codex-exec 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 yesterday.
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Exec — one-shot runtime adapter
Run exactly one caller-supplied Codex prompt and capture its result. This skill does not choose work, retry failures, validate by itself, or control continuation.
One prompt, one process, one captured artifact is what makes the run auditable: when nothing loops, every byte of output traces to exactly one invocation, and a disagreement about what happened is settled by the artifact.
Named failure mode — stdin hang: a non-TTY run left waiting forever on an open stdin nobody will write to; always pipe the prompt or close the stream.
Anti-pattern: granting workspace-write or network access "in case the prompt needs it". Corrective: match the sandbox to the declared effects; a review prompt runs read-only, full stop.
Procedure
- Confirm
codex login statusfor the intended profile. - Set the working root explicitly with
-C. - Match the sandbox to the requested effects: read-only for offline review, workspace-write for authorized edits, and broader access only when the caller explicitly requires network or external effects.
- Pipe the prompt to stdin (or close stdin) in non-TTY execution so the process cannot wait indefinitely for input.
- A wall-clock deadline is mandatory — never run codex unbounded. Use the
caller's deadline, or the declared default of 600s (10 min) when the
caller supplies none, and record which one applied. Enforce it so the whole
process tree is reaped, not just the direct child: run codex in its own
process group and kill the group on expiry:
setsid(own process group) +kill -KILL -<pgid>on the group;--kill-afteronly escalates TERM→KILL and plaintimeout <secs> codex …signals only the direct child. If the wrapper cannot guarantee process-group reaping, do not execute — that host lacks the cleanup capability this skill requires (capability unavailable, fail closed). Deadline expiry is fail-closed: the run is killed and reported as timed-out / not proven, partial output preserved — never a completed review. - Capture the final response with
-o, JSONL, or an output schema. - Report the typed run result, then stop: the process exit status, the captured
artifact path, which deadline applied and whether it fired, that the
process tree was reaped (a run without guaranteed reaping never starts), and whether
the
codexbinary was present at all. Cancellation is the caller's; this skill neither retries nor continues on its own.
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.
- yesterday First seen · 101 lines · 37 tokens per session scan A 7fd777a39758
codex-exec is a skill published in the GitHub repository boshu2/agentops (431 stars, last pushed 3d ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,074 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
brainstorm
Explore vague or ambitious ideas into a right-sized requirements-only plan. Use when the user wants to brainstorm, think through scope, decide what to build, or needs collaborative product framing before planning, not for a decisive verdict on whether to adopt or switch to a specific external technology, library, or…
doc-review
Use when the user asks to review or critique a prose planning document — a plan, spec, PRD, requirements doc, or design doc.
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
autolearn
Compound a solved problem into a durable in-repo learning doc. Use when a verified non-trivial fix lands, the user says "compound this", "document this fix", or "remember this". This is the automatic-capture entry point; for an explicitly requested one-off write-up, use compound.
doubt-driven
Doubt-driven adversarial review. Use when correctness matters more than speed, the code is unfamiliar, stakes are high, a claim can't be checked by the type system or compiler, or verifying now is cheaper than debugging later.
drift-detect
Use when the user says "plan drift", asks whether the roadmap, plans, or docs still match the code, or is deciding what to rebuild when restarting a stalled project. For doc-vs-code drift inside a specific diff, use sync-docs.