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 skills add yohey-w/kagemusha --skill codex-pro-plan-buildgit clone --depth 1 https://github.com/yohey-w/kagemushaWrote 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/yohey-w/kagemusha/codex-pro-plan-build)<a href="https://agentmods.dev/skills/yohey-w/kagemusha/codex-pro-plan-build"><img src="https://agentmods.dev/badge/skills/yohey-w/kagemusha/codex-pro-plan-build/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/yohey-w/kagemusha/codex-pro-plan-build"><img src="https://agentmods.dev/badge/skills/yohey-w/kagemusha/codex-pro-plan-build.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 | $0.00069 | $0.02382 |
| Opus 5.5 | $0.00028 | $0.00953 |
| Sonnet 5.5 | $0.00014 | $0.00476 |
| Haiku 4.5 | $0.00007 | $0.00238 |
Grade A, and why
codex-pro-plan-build 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 14d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Pro Plan and Build
Use a user-selected ChatGPT Web Pro model for the few decisions that could cause expensive rework, then use Codex to turn the audited result into a design contract, code, and tested evidence.
This is a procedure for Codex Desktop. It is not an automatic router, model configuration, quota policy, or guarantee that any named model is the strongest or free to use.
Required dependency
On the consultation route, before any external consultation, read and follow $codex-chatgpt-consult completely. That skill owns Browser availability, login and MFA handoff, visible model and mode verification, paste-card detection, single-send behavior, uncertain-send stops, complete verbatim capture, and hash/equality verification. Do not reproduce or bypass those controls here.
If consultation is required and $codex-chatgpt-consult or its in-app Browser capability is unavailable, stop. Do not substitute another browser, an API, a CLI, CDP, or custom browser automation. The local-only route does not require that dependency, Browser availability, login, or Web UI verification.
Boundaries
- Skill discovery is not permission to send anything externally. A request to implement code is not permission to send repository content to ChatGPT Web.
- Obey repository instructions, outbound controls, and the user's model choice. This skill never weakens security or overrides a stricter local rule.
- Treat the Pro response as advice. Check it against repository evidence and keep unsupported claims unresolved.
- A Pro model from the same provider lineage is not independent verification. Passing the repository's required tests and CI remains mandatory.
- Do not create a new task, child, or consultation automatically.
1. Establish the local baseline
Read the repository instructions before planning. Collect current evidence locally:
- repository root, current ref, and exact
HEAD; - working-tree status plus the relevant staged and unstaged diff, without disturbing unrelated changes;
- relevant implementation, interfaces, configuration, tests, documentation, and migration history;
- observed failures, commands already run, environmental constraints, and explicit user requirements;
- facts separated from inferences and unresolved questions.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 14d ago Changed 77a773c1f1cb
- 25d ago First seen · 144 lines · 69 tokens per session scan A bbee131cfe6c
codex-pro-plan-build is a skill published in the GitHub repository yohey-w/kagemusha (16 stars, last pushed 5d ago), licensed MIT. It adds 69 tokens to every session and 2,382 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 2026-09-21.
Other skills, from other repositories
loop-builder
A design workbench for turning a vague task into a controlled, repeatable Agent Loop. An Agent Loop is a task process with defined steps, checks, stopping points, and recovery actions.
ui-visual-match-replicator
A screenshot-driven workflow for rebuilding a webpage or frontend so its rendered appearance matches a supplied visual. It compares screenshots, identifies the largest differences, and repeats the implementation and correction cycle.
akg-agents
An agent workflow for developing, generating, testing, and tuning AKG operators. AKG is a toolkit for generating optimized computational kernels.
openJiuwen-DeepSearch
A deep-research tool that plans searches, gathers and checks information, and produces research reports in Markdown, DOC, or HTML format. It coordinates several AI agents for complex investigations.
tencent-ima-wiki
A browser-automation workflow for reading articles from a logged-in Tencent ima knowledge base. It extracts article links and text from the ima.qq.com/wikis site, including pages whose details are not directly visible in the webpage.
my-custom-skill
Example custom agent skill — a template to get started.