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/andyzengmath/quantum-loop/ql-reviewnpx skills add andyzengmath/quantum-loop --skill ql-reviewgit clone --depth 1 https://github.com/andyzengmath/quantum-loopWhat 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 | $0.00062 | $0.01627 |
| Opus 5 | $0.00031 | $0.00813 |
| Sonnet 5 | $0.00012 | $0.00325 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
ql-review 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.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quantum-Loop: Review
You orchestrate a two-stage code review. Stage 1 (spec compliance) MUST pass before Stage 2 (code quality) begins. This order is absolute.
Why Two Stages?
Code that doesn't match the spec is waste -- no matter how well-written. Checking spec compliance first prevents spending review effort on code that needs to be rewritten anyway.
Usage Modes
Mode 1: Within /quantum-loop:execute (automated)
Called automatically by the execution loop after a story's quality checks pass. Receives story context from quantum.json.
Mode 2: Standalone (user-invoked)
User invokes /quantum-loop:review directly to review recent changes.
Standalone Workflow
Step 1: Determine Review Scope
If the user specifies a story ID, use it. Otherwise:
- Check for
quantum.json-- if exists, identify the most recentin_progressstory - If no quantum.json, use the current branch's diff from main/master:
git merge-base HEAD main
Determine BASE_SHA and HEAD_SHA for the review range.
Step 2: Identify the Spec
- If quantum.json exists: read the PRD path and story acceptance criteria
- If no quantum.json: ask the user what requirements this code should meet
- If no spec exists at all: skip Stage 1, proceed directly to Stage 2 with a warning
Step 3: Stage 1 -- Spec Compliance Review
Dispatch the spec-reviewer agent with:
- STORY_ID
- PRD_PATH
- BASE_SHA
- HEAD_SHA
Wait for the review result.
If Stage 1 PASSES:
- Log result to quantum.json (if available)
- Proceed to Stage 2
If Stage 1 FAILS:
- Present the issues to the user (or to the execution loop)
- List every unsatisfied acceptance criterion with evidence
- Do NOT proceed to Stage 2
- If within /quantum-loop:execute: return failure with issues list
Step 4: Stage 2 -- Code Quality Review
Only reached if Stage 1 passed.
Dispatch the quality-reviewer agent with:
- STORY_ID
- BASE_SHA
- HEAD_SHA
- DESCRIPTION (brief summary of what was implemented)
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 · 184 lines · 62 tokens per session scan A 150a380eb8dd
ql-review is a skill published in the GitHub repository andyzengmath/quantum-loop (24 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 1,627 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
token-coach
Plan a token-efficient Claude Code or Codex setup, or get a quick health check. Coaching, not the full audit (use token-optimizer for that).
token-optimizer
Audit a Claude Code or Codex setup for context-window waste, then fix it and measure the savings. Use when context feels tight.
fleet-auditor
Cross-system agent token/cost audit (Claude Code, Codex, OpenClaw, Hermes, OpenCode): idle burns, model misrouting, config bloat, with dollar savings.
gdpr-compliance-checker
Autonomous GDPR compliance auditor that scans a codebase to identify PII collection, storage, and sharing, then produces an article-by-article gap analysis, a pre-filled Data Processing Agreement (DPA), and a ROPA (Record of Processing Activities) starter kit — all exported as downloadable files (.docx recommended).…
pii-detector
Proactive PII add-on — augments the main response with PII guidance. Auto-trigger on any form, schema, migration, model, API route, GraphQL resolver, auth flow, or data design discussion. Also fires on: middleware, webhooks, workers, seed/fixture/factory files, delete/export/purge/anonymize functions, cron jobs, HTTP…