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/quick)<a href="https://agentmods.dev/commands/vsladkov/claudex-stereo/quick"><img src="https://agentmods.dev/badge/commands/vsladkov/claudex-stereo/quick/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/commands/vsladkov/claudex-stereo/quick"><img src="https://agentmods.dev/badge/commands/vsladkov/claudex-stereo/quick.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.02252 |
| Opus 5.5 | $0.00008 | $0.00901 |
| Sonnet 5.5 | $0.00004 | $0.00450 |
| Haiku 4.5 | $0.00002 | $0.00225 |
Grade A, and why
quick 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 21d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First Read ${CLAUDE_PLUGIN_ROOT}/skills/model-routing/SKILL.md, then
${CLAUDE_PLUGIN_ROOT}/skills/model-routing/pair-procedures.md,
${CLAUDE_PLUGIN_ROOT}/skills/model-routing/plan-procedures.md, and
${CLAUDE_PLUGIN_ROOT}/skills/model-routing/implement-procedures.md — plus
${CLAUDE_PLUGIN_ROOT}/skills/model-routing/worktree-procedure.md for an --isolated run — and
apply their rules. The rules below are step-specific; a quoted heading names the section of a
routing file that defines the step.
Run both Stereo phases for one small task. Preserve the canonical /stereo:plan and
/stereo:implement semantics with fixed quick safeguards and no approval gate between an approved
plan and implementation.
Raw slash-command arguments:
$ARGUMENTS
Arguments and role defaults
Parse all arguments per "Selection and effort parsing" before repository work, then read the "Workspace role defaults" and say in the effective-role recap which role a workspace default supplied:
--planner,--plan-reviewer,--implementer, and--implementation-reviewerselect the four roles, each with its-effortflag. The scope gate still runs inline in this session before any routed draft.--slot <name>selects the durable plan slot this run stores into and defaults todefault. Slot names are trimmed, lowercased, may contain only letters, digits, hyphens, and underscores, and must start with a letter or digit. Relay the CLI's validation error verbatim.--max-plan-rounds <n>defaults to 2 and must be an integer from 1 to 6; above 6, point at/stereo:planfor a longer plan-review loop.--max-fix-rounds <n>defaults to 2 and must be a positive integer. Direct gate-fix turns and review-driven fix turns both count toward it; the implementer's own inner-loop iterations never do.--isolatedruns implementation, implementation review, and fixes in a throwaway detached git worktree and hands the delta back as a user-confirmed patch; the plan draft and every plan-review round still run against the main tree.- Remaining text is the task. Ask for it if empty.
/stereo:quick has no --resume: an interrupted Quick run restarts from the beginning. Use
/stereo:plan plus /stereo:implement for a long task that needs durable phase state. Quick
writes no implementation record, so a crash during an --isolated run strands the worktree with no
durable pointer to it; Quick prints <worktreePath> at creation, and /stereo:doctor lists every
stranded stereo-worktrees entry with its removal command.
Keep these ids distinct and never cross-assign them: plannerThreadId (the companion draft),
planReviewThreadId (companion plan-review payloads), implementationThreadId (companion
implementation and fix payloads), and implementationReviewThreadId (companion
implementation-review tasks).
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.
- 21d ago Changed · -678 lines a6241dd3f23e
- 1mo ago Changed · -1 lines 80e2c4e5141d
- 1mo ago Changed · +1 lines 21648878ae34
- 1mo ago First seen · 839 lines · 19 tokens per session scan A 6539ed58b6fb
quick is a command published in the GitHub repository vsladkov/claudex-stereo (4 stars, last pushed 21d ago), licensed Apache-2.0. It adds 19 tokens to every session and 2,252 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
check
Quick sanity check - code (inline 6-perspective) or plan (--plan).
end
End a work session - a settlement pass that reconciles uncommitted / unpushed work + session context into git, the tracker, and a session snapshot file. --session (aliases --snapshot, --pre-compact, --compact) skips settlement and only writes the shared snapshot, keeping the session going.
note
Add a note to the active task - progress, decisions, context. --session (aliases --snapshot, --pre-compact, --compact) writes a resume-grade session snapshot without ending the session. --team writes a fact or a decision into the standing team's file.
review-round
Work through a RECEIVED round of review comments (inline markers, a review file, or PR threads) on a spec/doc/PR. Triage each item, record decisions to the tracker task, keep the artifact FROZEN, then apply all edits in ONE final pass. Use when a reviewer returns N comments to incorporate.
hub
Cross-project hub on Orca - see every project's orchestrators, ask a stopped one read-only, wake one for gated work (Orca addon).
statusline
Manage & persist statusline appearance - light/dark, compact, and which rows to show.