Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add vsladkov/claudex-stereo/plugin install stereoWrote 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/commands/vsladkov/claudex-stereo/cancel)<a href="https://agentmods.dev/commands/vsladkov/claudex-stereo/cancel"><img src="https://agentmods.dev/badge/commands/vsladkov/claudex-stereo/cancel.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00010 | $0.00264 |
| Opus 5 | $0.00005 | $0.00132 |
| Sonnet 5 | $0.00002 | $0.00053 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
cancel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
!node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.ts" cancel "$ARGUMENTS"
Use --workspace <path> to cancel jobs recorded against another repository root, such as the main
workspace used by a worktree-isolated /stereo:implement --isolated or /stereo:tournament run.
Present the rendered result verbatim without summarizing it. Preserve any
Stored job file is unreadable: warning and its path.
Relay these failure paths exactly and follow each with a direction to run /stereo:status:
No active job found for "<ref>".Job reference "<ref>" is ambiguous. Use a longer job id.Multiple Codex jobs are active. Pass a job id to /stereo:cancel.No active Codex jobs to cancel for this session.A job owned by another session is reachable only by explicit id; also direct the user to/stereo:status --all.No active Codex jobs to cancel.
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.
- 5d ago First seen · 24 lines · 10 tokens per session scan A d598b0766054
cancel is a command published in the GitHub repository vsladkov/claudex-stereo (3 stars, last pushed 27d ago), licensed Apache-2.0. It adds 10 tokens to every session and 264 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
duck-off
Turn off Rubber Duck mode and answer normally.
save
Save the current session digest. Fans out across every writable memory tier per the house-map. Tier 0 always; Tier 1 if reachable; Tier 2 only if registered writable with auth. Each tier independent — failures degrade gracefully.
notice
Maude surfaces patterns from the turn-by-turn trace — recurring topics, repeated mistakes, time-of-day patterns, sessions that keep ending in the same place.
promote
Show what the tape is holding for your word, and promote the ones you approve into canon. Agent inference never becomes canon on its own — this is the door, and your hand is on it.
check-on-claude
Maude checks on Claude — repeated tool calls, unread context, confabulation risk, missed CLAUDE.md, the patterns Claude doesn't see in himself.
gate
The consensus gate — opt this repo in (or out) of duet-signed commits.