Borrowing it
Nothing to install: this file belongs to gpt-cmdr/ras-commander. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gpt-cmdr/ras-commander/main/.agents/native-skills/dev_invoke_claude-code/SKILL.mdgit clone --depth 1 https://github.com/gpt-cmdr/ras-commanderWrote 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/gpt-cmdr/ras-commander/dev_invoke_claude-code)<a href="https://agentmods.dev/skills/gpt-cmdr/ras-commander/dev_invoke_claude-code"><img src="https://agentmods.dev/badge/skills/gpt-cmdr/ras-commander/dev_invoke_claude-code/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/gpt-cmdr/ras-commander/dev_invoke_claude-code"><img src="https://agentmods.dev/badge/skills/gpt-cmdr/ras-commander/dev_invoke_claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00163 | $0.01337 |
| Opus 5.5 | $0.00065 | $0.00535 |
| Sonnet 5.5 | $0.00033 | $0.00267 |
| Haiku 4.5 | $0.00016 | $0.00134 |
Grade A, and why
dev_invoke_claude-code 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 1mo 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invoking Claude Code For QAQC
Codex-native provider handoff skill. This is not a shared domain workflow and should not be mirrored into
.claude/skills/. It lets Codex request an independent Claude Code review while keeping shared repo policy inAGENTS.md.
Use this skill when the user explicitly asks Codex to have Claude Code review code, documentation, notebooks, or agent-framework changes.
Safety Rules
- Use Claude as a read-only reviewer by default.
- Do not let Claude edit files, commit, push, install tools, or mutate the worktree.
- Do not overwrite root-level
TASK.mdorOUTPUT.md; those may belong to another handoff. - Put each review in an ignored workspace such as
working/agent-reviews/claude-code/{timestamp}-{slug}/. - Give Claude the same shared repo contract Codex used: nearest
AGENTS.md, relevant localAGENTS.mdfiles, and task-specific files. - Do not use
--dangerously-skip-permissionsunless the user explicitly requests it and the workspace is externally sandboxed.
Handoff Pattern
Create a review workspace:
$reviewDir = "working/agent-reviews/claude-code/20260426-claude-qaqc"
New-Item -ItemType Directory -Force $reviewDir | Out-Null
Write TASK.md in that folder. Include:
- the review target files or directories
- the exact concern or review objective
- the shared instruction files Claude should read first
- a strict read-only constraint
- the expected finding format
Minimum TASK.md shape:
# Claude Code QAQC Review
You are performing an independent read-only QAQC review for ras-commander.
## Read First
1. AGENTS.md
2. The nearest local AGENTS.md files for the target paths
3. docs/development/multi-harness-agent-contract.md when reviewing agent infrastructure
## Target
- path/to/file_or_directory
## Review Focus
- correctness bugs
- behavioral regressions
- missing tests or validation gaps
- security or supply-chain risks, if relevant
## Constraints
- Do not edit files.
- Do not run destructive commands.
- Do not commit or push.
- Write findings first, ordered by severity.
- Include file and line references when possible.
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.
- 1mo ago First seen · 169 lines · 163 tokens per session scan A 1183c7fc922e
dev_invoke_claude-code is a skill published in the GitHub repository gpt-cmdr/ras-commander (88 stars, last pushed today), licensed MIT. It adds 163 tokens to every session and 1,337 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…