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/zebbern/agent-collab/rescuegit clone --depth 1 https://github.com/zebbern/agent-collabWhat 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 | $0.00020 | $0.01012 |
| Opus 5 | $0.00010 | $0.00506 |
| Sonnet 5 | $0.00004 | $0.00202 |
| Haiku 4.5 | $0.00002 | $0.00101 |
Grade A, and why
rescue 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.
This is a copy
95% identical to rescue — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Invoke the codex:codex-rescue subagent via the Agent tool (subagent_type: "codex:codex-rescue"), forwarding the raw user request as the prompt.
codex:codex-rescue is a subagent, not a skill — do not call Skill(codex:codex-rescue) (no such skill) or Skill(codex:rescue) (that re-enters this command and hangs the session). The command runs inline so the Agent tool stays in scope; forked general-purpose subagents do not expose it.
The final user-visible response must be Codex's output verbatim.
Raw user request: $ARGUMENTS
Execution mode:
- If the request includes
--background, run thecodex:codex-rescuesubagent in the background. - If the request includes
--wait, run thecodex:codex-rescuesubagent in the foreground. - If neither flag is present, default to foreground.
--backgroundand--waitare execution flags for Claude Code. Do not forward them totask, and do not treat them as part of the natural-language task text.--modeland--effortare runtime-selection flags. Preserve them for the forwardedtaskcall, but do not treat them as part of the natural-language task text.--profile <deep|fast>is also a runtime-selection flag. Preserve it for the forwardedtaskcall, but do not treat it as part of the natural-language task text.--profilesupplies default model/effort; an explicit--modelor--efforton the same request overrides the profile's default for that field.- If the request includes
--resume, do not ask whether to continue. The user already chose. - If the request includes
--fresh, do not ask whether to continue. The user already chose. - Otherwise, before starting Codex, check for a resumable rescue thread from this Claude session by running:
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" task-resume-candidate --json
- If that helper reports
available: true, useAskUserQuestionexactly once to ask whether to continue the current Codex thread or start a new one. - The two choices must be:
Continue current Codex threadStart a new Codex thread
- If the user is clearly giving a follow-up instruction such as "continue", "keep going", "resume", "apply the top fix", or "dig deeper", put
Continue current Codex thread (Recommended)first. - Otherwise put
Start a new Codex thread (Recommended)first. - If the user chooses continue, add
--resumebefore routing to the subagent. - If the user chooses a new thread, add
--freshbefore routing to the subagent. - If the helper reports
available: false, do not ask. Route normally.
Operating rules:
- The subagent is a thin forwarder only. It should use one
Bashcall to invokenode "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" task ...and return that command's stdout as-is. - Return the Codex companion stdout verbatim to the user.
- Do not paraphrase, summarize, rewrite, or add commentary before or after it.
- Do not ask the subagent to inspect files, monitor progress, poll
/codex:status, fetch/codex:result, call/codex:cancel, summarize output, or do follow-up work of its own. - Leave
--effortunset unless the user explicitly asks for a specific reasoning effort. - Leave the model unset unless the user explicitly asks for one. If they ask for
spark, map it togpt-5.3-codex-spark. - Leave
--resumeand--freshin the forwarded request. The subagent handles that routing when it builds thetaskcommand. - If the helper reports that Codex is missing or unauthenticated, stop and tell the user to run
/codex:setup. - If the user did not supply a request, ask what Codex should investigate or fix.
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 · 51 lines · 20 tokens per session scan A bd0bf03b68c7
rescue is a command published in the GitHub repository zebbern/agent-collab (32 stars, last pushed 17d ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,012 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to rescue, differing in 3 lines, and is treated as a copy.
Other commands, from other repositories
create-skill
Create an AI skill from any source (URL, repo, PDF, video, notebook, etc.).
paul:research-phase
Research unknowns for a phase using subagents.
pack-repo
Pack la codebase en un fichier AI-friendly (Repomix wrapper + fallback shell). Token counting inclus.
auto-implement-tasks
Enhanced auto-implementation with intelligent code generation and testing.
claude-devtools:explain-visible-context
Explains what "Visible Context" is — the 6 trackable token categories, what falls outside tracking, how it's displayed, and why it matters. Use when someone asks about visible context, token attribution, or context window usage.
setup-agents
Scaffold a multi-agent AI setup for any repo. Scans the codebase, interviews the developer, generates agent configs for whichever AI tools the repo uses (Copilot, Claude Code, Cursor, Codex, Windsurf). Use when asked to "set up agents", "scaffold Copilot agents", or "create an AGENTS.md".