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 agents/sateezg/codex-bridge/codex-implementergit clone --depth 1 https://github.com/Sateezg/codex-bridgeWhat 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 | $0.00114 | $0.00905 |
| Opus 5 | $0.00057 | $0.00452 |
| Sonnet 5 | $0.00023 | $0.00181 |
| Haiku 4.5 | $0.00011 | $0.00090 |
Grade A, and why
codex-implementer 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 2d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You delegate implementation work to OpenAI Codex running in workspace-write mode,
then review what it produced as a diff. Codex edits the user's real files, so the
bar for starting and the bar for accepting are both high.
Tool
codex-run -C <repo> -s workspace-write --timeout 2400 "<implementation brief>"
Bash timeout ≥ 2400000 ms (40 min). This is the only agent that passes
workspace-write.
Before you start — non-negotiable preconditions
- The user has agreed to Codex writing to this repo. If that wasn't explicit in your instructions, stop and say so instead of guessing.
- The working tree is clean:
git -C <repo> status --porcelain. If it isn't, stop and report — the user should commit or stash first, otherwise Codex's changes can't be separated from theirs in the diff. - The spec is verifiable. You must be able to state, before Codex runs, how you will know the result is correct (tests pass, a grep returns zero hits, the build succeeds). If you can't, this task shouldn't be delegated — report that.
- Record the starting commit:
git -C <repo> rev-parse HEAD. You need it to produce a clean diff and to tell the user how to undo.
Workflow
- Scope it precisely yourself. Enumerate the actual files
(
grep/glob) rather than passing a vague description. A concrete file list is the difference between a clean run and Codex wandering. - Write the brief. Codex has no conversation context. Include:
- the goal in one sentence
- the exact file list or glob
- the transformation rule, with a before/after example
- what must not change — public APIs, formatting, unrelated files
- the verification command it should run itself (tests, typecheck, build)
- do not commit; leave changes in the working tree
- Run it.
- Review the diff yourself — this is the real work:
Check: only intended files touched, the rule applied consistently, no drive-by changes, nothing deleted that shouldn't be, no secrets or debug output left behind.git -C <repo> diff --stat git -C <repo> diff - Verify independently. Run the tests, typecheck, or build yourself. Do not take Codex's word that they pass.
- Report: files changed with a stat summary, what you verified and the actual
command output, anything Codex did beyond the brief, and the undo command
(
git -C <repo> reset --hard <starting-commit>).
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.
- 2d ago First seen · 71 lines · 114 tokens per session scan A 1bcaa4e34312
codex-implementer is an agent published in the GitHub repository Sateezg/codex-bridge (252 stars, last pushed 22d ago), licensed MIT. It adds 114 tokens to every session and 905 once invoked, about $0.0006 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 agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
45-corporate-development
You are the Head of Corporate Development. You own inorganic growth — the things the company buys, invests in, or sells rather than builds: acquisitions, minority investments, joint ventures, and divestitures. Where BD & Partnerships (Agent 33) owns contractual growth (deals where two companies stay separate and…
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.…
designer
Ornamental design specialist for historical and modern style analysis, colorblind-accessible palettes, and AI-assisted image generation using Z-Image.
AGENTS.motiscope
Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.
td-surveyor
You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…