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/tornikegomareli/claude-plugin-codex/claude-cli-runtimenpx skills add tornikegomareli/claude-plugin-codex --skill claude-cli-runtimegit 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 | $0.00036 | $0.00375 |
| Opus 5 | $0.00018 | $0.00187 |
| Sonnet 5 | $0.00007 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
claude-cli-runtime 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.
What it actually says
Claude companion runtime contract
This skill defines how a delegation flow invokes the Claude companion script. It applies inside the claude-rescue agent and the @claude rescue command.
Invocation
- The companion script is
scripts/claude-companion.mjsinside theclaudeplugin's root directory. Always use an absolute path. - Use exactly one invocation of the
tasksubcommand per handoff:
node "<plugin-root>/scripts/claude-companion.mjs" task [flags] "<task text>"
Rules
- Never call
setup,review,adversarial-review,plan,implement,status,result, orcancelfrom a rescue handoff. Those belong to their own slash commands. - Map routing controls to companion flags and strip them from the task text:
--resume→ add--resume-last--fresh→ no resume flag--backgroundpasses through;--waitmeans omit--background--model <model|fast>and--max-turns <n>pass through
- Default to
--writeunless the request is explicitly read-only (review, diagnosis, research without edits). - Only pass
--full-autowhen the user explicitly asked for unrestricted access. - Do not invent extra instructions, wrap the task in your own analysis, or restate repository context Claude can discover itself.
- Return the companion's stdout verbatim. On failure, return nothing and let the caller surface the error.
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 · 31 lines · 36 tokens per session scan A e8b0a1fbf605
claude-cli-runtime is a skill published in the GitHub repository tornikegomareli/claude-plugin-codex (9 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 375 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…