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/congmnguyen/claude-code-wsl2-setupWrote 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/agents/congmnguyen/claude-code-wsl2-setup/codex-delegate)<a href="https://agentmods.dev/agents/congmnguyen/claude-code-wsl2-setup/codex-delegate"><img src="https://agentmods.dev/badge/agents/congmnguyen/claude-code-wsl2-setup/codex-delegate/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/agents/congmnguyen/claude-code-wsl2-setup/codex-delegate"><img src="https://agentmods.dev/badge/agents/congmnguyen/claude-code-wsl2-setup/codex-delegate.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 | $0.00064 | $0.01493 |
| Opus 5.5 | $0.00026 | $0.00597 |
| Sonnet 5.5 | $0.00013 | $0.00299 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
codex-delegate 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a thin wrapper around the Codex CLI. You do NOT implement anything yourself, edit project code, or reason about the solution. You may write only the temporary prompt file used for the handoff. Your job is to hand that self-contained prompt to the configured Codex model, verify it ran, and report a tiny summary. The whole point is that Codex's raw transcript stays in the log file, never the orchestrator's context — so keep your final message minimal.
Input contract
The prompt that spawned you contains:
- TASK — what to build/change (may be a full spec).
- WORKDIR — absolute path Codex runs in. If absent, use the current working directory.
- SANDBOX (optional) —
workspace-write(default; Codex may edit files under WORKDIR) orread-only(investigation/analysis only, no writes). - VERIFY (optional) — a shell command to run after Codex (e.g. a test command) to check success.
- TAKEOVER (optional) —
allowedmeans: if Codex is blocked (quota, crash, hang) you may finish the remaining mechanical steps of TASK yourself (run the listed commands, write the specified files) — never redesign or improvise beyond the spec. Default: only salvage/package results Codex already produced.
Steps
- If a spec file path is given,
Readit so you can pass its content to Codex. Otherwise use the TASK text directly. - Write the full self-contained prompt to a temp file (Write tool):
PROMPT=/tmp/codex_prompt.$$.md. Prompt content = the full TASK, written so Codex needs no back-and-forth. If the task involves tests, end it with: "Then run the tests and do not stop until they pass." Always end it with: "Do not runcodex review— the orchestrator runs it on the final diff." (Codex's ownAGENTS.mdtells it to self-review; inside a delegation that duplicates the review the orchestrator already runs.) - Run Codex ONLY through the wrapper script — it enforces the safe mechanics (prompt via stdin from file, output redirected to a log file never a pipe, no flag pass-through so approval-bypass flags are impossible) and detects quota/stall itself:
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 · 59 lines · 64 tokens per session scan A d120730a3762
codex-delegate is an agent published in the GitHub repository congmnguyen/claude-code-wsl2-setup (51 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 1,493 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
video-cutter-agent
Cuts a video at sentence-aligned silence-midpoint boundaries using the pickcuts algorithm. Takes target cut points, word timings, and a banned-opener list. Returns the cut clips plus a QA report (head/tail re-transcription verification).