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/tornikegomareli/claude-plugin-codex/implementgit clone --depth 1 https://github.com/tornikegomareli/claude-plugin-codexWhat 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 | $0.00040 | $0.00536 |
| Opus 5 | $0.00020 | $0.00268 |
| Sonnet 5 | $0.00008 | $0.00107 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
implement 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.
What it actually says
Delegate an implementation to Claude Code. Claude will edit files in this repository.
Raw slash-command arguments:
$ARGUMENTS
Locating the companion script:
- The companion script is
scripts/claude-companion.mjsinside this plugin's root directory (the installedclaudeplugin directory that contains.codex-plugin/plugin.json). - Always invoke it with an absolute path.
Before running:
- Tell the user this run will make code changes in the working tree.
- If the working tree already has uncommitted changes, mention that briefly so the user can separate Claude's edits later.
Plan sources (mutually exclusive, pass through unchanged):
--resume-plancontinues the latest@claude plansession with edit permissions. Prefer this when the user just ran@claude plan.--from-plan <job-id>inlines the stored plan text from that job.--plan-file <path>reads a plan from a file.- With none of these, the positional text is the implementation task itself.
Execution mode rules:
- If the raw arguments include
--wait, run in the foreground without asking. - If the raw arguments include
--background, run with--backgroundwithout asking. - Otherwise ask the user exactly once, in plain conversation, with "Run in background (Recommended)" first — implementations usually take a while.
Flow:
- Run:
node "<plugin-root>/scripts/claude-companion.mjs" implement "$ARGUMENTS"
- Return the output verbatim, exactly as-is.
- After a completed foreground run, suggest
@claude review --waitto review the changes. Do not run the review yourself. - For background runs, tell the user: "Claude is implementing in the background. Check
@claude statusfor progress." --full-autogives Claude unrestricted tool access for the run; only pass it through when the user explicitly asked for it.
Sandbox requirements:
- The companion spawns the
claudeCLI, which needs network access to reach the Anthropic API. - If the sandbox blocks the command or Claude reports a connection error, rerun the same shell command with escalated permissions and explain why in the justification.
- Do not work around a sandbox denial by improvising your own review or edits; the command's value is Claude's independent output.
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 · 43 lines · 40 tokens per session scan A 5397cfac10e5
implement is a command published in the GitHub repository tornikegomareli/claude-plugin-codex (9 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 536 once invoked, about $0.0002 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.