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 commands/dropfan/claude-code-plugins/codex-reviewgit 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 | $0.00016 | $0.02067 |
| Opus 5 | $0.00008 | $0.01033 |
| Sonnet 5 | $0.00003 | $0.00413 |
| Haiku 4.5 | $0.00002 | $0.00207 |
Grade A, and why
codex-review 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Working directory: !
pwd - Codex installed: !
codex --version 2>&1 || echo "NOT INSTALLED" - Current branch: !
git branch --show-current 2>/dev/null || echo "NOT A GIT REPO" - Uncommitted changes: !
git status --short 2>/dev/null | head -20
Task
Run Codex CLI code review with deep context enrichment and structured analysis.
User arguments: $ARGUMENTS
Pre-checks
- If Codex is not installed (version shows "NOT INSTALLED"), tell the user to install it with
npm install -g @openai/codexand configure withcodex login. Stop here. - If not in a git repo (branch shows "NOT A GIT REPO"), tell the user this command requires a git repository. Stop here.
- If uncommitted changes is empty AND ($ARGUMENTS is empty OR $ARGUMENTS is
uncommitted), tell the user there are no uncommitted changes and suggest specifying a branch or commit SHA (e.g.,/codex-bridge:codex-review main). Stop here.
Step 1: Determine Review Scope
Parse $ARGUMENTS to decide the review mode. When ambiguous, verify with git before deciding:
git branch --list "$ARGUMENTS" 2>/dev/null # non-empty → branch
git rev-parse --verify "$ARGUMENTS^{commit}" 2>/dev/null # success → valid commit
| $ARGUMENTS | Mode | Base Command |
|---|---|---|
Empty or uncommitted |
Uncommitted changes | codex review --uncommitted |
| Verified as a branch name | Branch diff | codex review --base $ARGUMENTS |
| Verified as a commit SHA | Single commit | codex review --commit $ARGUMENTS |
| Contains natural language | Guided review | codex review "<enriched prompt>" |
Important: Codex CLI does not allow
--uncommittedand[PROMPT]together. When providing custom instructions, pass them as the positional argument only — Codex defaults to reviewing uncommitted changes when no scope flag is given.
Step 2: Collect Deep Context
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 · 173 lines · 16 tokens per session scan A 9fbdd5731616
codex-review is a command published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 26d ago), licensed MIT. It adds 16 tokens to every session and 2,067 once invoked, about $0.0001 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 commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
full
Run the full hope pipeline — intent, shape, target, freeze as needed — then execute.
status
Show tlive daemon, channel, and Codex companion status.
csv-to-numbers
Convert a CSV into a formatted Numbers workbook.
rust-critique
Deep code critique — read the target Rust code and apply the full review process. Evaluates soundness, ownership, error handling, type design, async correctness, performance, and architecture. Think like a senior Rust engineer giving honest feedback.
dotnet-structure
Analyze and recommend .NET backend solution and folder structure improvements. Checks projects, layers, oversized files, and boundary clarity.