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 lzhgus/cc-plugin-codex --skill claude-promptinggit clone --depth 1 https://github.com/lzhgus/cc-plugin-codexWrote 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/lzhgus/cc-plugin-codex/claude-prompting)<a href="https://agentmods.dev/skills/lzhgus/cc-plugin-codex/claude-prompting"><img src="https://agentmods.dev/badge/skills/lzhgus/cc-plugin-codex/claude-prompting/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/lzhgus/cc-plugin-codex/claude-prompting"><img src="https://agentmods.dev/badge/skills/lzhgus/cc-plugin-codex/claude-prompting.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 | $0.00042 | $0.00399 |
| Opus 5.5 | $0.00017 | $0.00160 |
| Sonnet 5.5 | $0.00008 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
claude-prompting 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 2mo 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.
What it actually says
Prompting Claude Code from Codex
Overview
When you delegate to Claude Code through cc_rescue or aim a cc_review / cc_adversarial_review, the quality of the result depends on how you phrase the task. Claude Code is a full agent with its own tools (Read, Edit, Bash, …), so give it a goal and constraints, not a script.
Principles
- State the goal, then the constraints. "Fix the flaky login test. Don't touch auth.go; the bug is in the test's retry timing."
- One task at a time. Don't bundle five asks into one rescue. If the user asks for several things, sequence them and say so.
- Point at files when you know them. "The regression is likely in
pkg/repo/cache.go." Claude can search, but a pointer saves time. - Ask for verification. Add "run the project's tests before declaring done" for fixes. Claude Code does this by default via its own instructions, but restating it helps.
- Prefer background for long work. Pass
background: trueand tell the user the task id.
For reviews
cc_reviewneeds no focus text — just the target (uncommitted, orbase).cc_adversarial_reviewbenefits from a concretefocus: name the risk area. "Look for race conditions in the new cache and question the chosen eviction policy" beats "review the code".
Antipatterns
See [[references/prompt-antipatterns]] for things to avoid, and [[references/prompt-recipes]] for copy-pasteable task shapes.
What ships with it
2 files 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.
- 2mo ago First seen · 27 lines · 42 tokens per session scan A 506915c35e0c
claude-prompting is a skill published in the GitHub repository lzhgus/cc-plugin-codex (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 399 once invoked, about $0.0002 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 2026-08-31.
claude-prompting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-promptinglzhgus/cc-plugin-codex | Skill | 11 | 4mo ago | Apache-2.0 | A | 42 | Claude Code, Codex |
| llm-app-patternsdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 54 | Claude Code, Codex |
| prompt-engineerJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 93 | Claude Code |
| prompt-optimizationlangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 105 | Claude Code, Codex |
| omh-model-optimizationrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 84 | Claude Code, Codex |
| ideogram4digitalsamba/claude-code-video-toolkit | Skill | 2.5k | yesterday | MIT | A | 99 | Claude Code |
| prompt-library-for-startupsaws/agent-toolkit-for-aws | Skill | 3.4k | yesterday | Apache-2.0 | A | 228 | Claude Code |