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/dropfan/claude-code-plugins/codexnpx skills add DropFan/claude-code-plugins --skill codexgit clone --depth 1 https://github.com/DropFan/claude-code-pluginsWhat 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 | $0.00170 | $0.00822 |
| Opus 5 | $0.00085 | $0.00411 |
| Sonnet 5 | $0.00034 | $0.00164 |
| Haiku 4.5 | $0.00017 | $0.00082 |
Grade A, and why
codex 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Bridge
Route user requests to the appropriate Codex command. Commands handle context collection, prompt composition, and result analysis autonomously.
Safety
- Default sandbox:
read-only. Only useworkspace-writeon explicit user request. - Forbidden flags:
--dangerously-bypass-approvals-and-sandbox(and its alias--yolo),--full-auto,--sandbox danger-full-access - Never pass secrets (API keys, tokens, passwords) in Codex prompts.
Intent Classification & Routing
Classify the user's request and invoke the matching command. When the intent is ambiguous (e.g., "codex check this"), look at conversation context — if the user was just editing code and has uncommitted changes, lean toward review; otherwise default to general task.
Review Intent → /codex-bridge:codex-review
Trigger when the request is about reviewing code changes, diffs, commits, or PRs.
Keywords: review, 审查, check changes, 看看改动, code review, PR review, diff review, check my code, 看看代码
Examples:
- "让 codex review 我的改动" →
/codex-bridge:codex-review - "codex 审查一下这个 PR" →
/codex-bridge:codex-review - "ask codex to review changes against main" →
/codex-bridge:codex-review main - "codex check my latest commit" →
/codex-bridge:codex-review HEAD
Pass any branch name, commit SHA, or review instructions as arguments.
General Task → /codex-bridge:codex
Trigger for all other requests: analysis, verification, second opinion, document review, task delegation.
Keywords: analyze, verify, explain, compare, delegate, check, 分析, 验证, 看看, 帮忙看
Examples:
- "让 codex 分析这个函数的错误处理" →
/codex-bridge:codex "分析...的错误处理" - "ask codex about the auth implementation" →
/codex-bridge:codex "analyze the auth implementation" - "codex 帮我看看这个插件的安全性" →
/codex-bridge:codex "review the security of this plugin"
Pass the user's full request as the argument. The command will resolve context and compose the prompt.
Ambiguous Cases
When the user's intent could match either command:
- If the user mentions "changes", "diff", "commit", or "PR" → review
- If the user mentions a specific file or function to analyze → general task
- If still unclear, ask the user: "Would you like Codex to review your recent changes, or analyze something specific?"
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.
- yesterday First seen · 65 lines · 170 tokens per session scan A 8c77e9a657ae
codex is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 26d ago), licensed MIT. It adds 170 tokens to every session and 822 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
agent-check
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
skill-check
Validate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.
agent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
session-relay
Continue real repository work between Claude Code, Codex CLI, and Grok Build with a privacy-bounded, drift-aware handoff packet. Use for cross-vendor takeover, context-limit checkpoints, multi-hop Claude→Codex→Grok relays, or receiving an existing Director packet. Use native resume commands for same-CLI history; never…