ql-deep-review

A whole-feature review that combines findings from multiple reviewer agents after individual stories pass their reviews.

In plain words
What is it for?
Reviewing a completed wave or feature before merging, checking cross-story consistency, post-merge behavior, alignment with the original intent, and whether reported issues are actionable.
Why use it?
Story-by-story checks can miss disagreements between stories, regressions after merging, drift from the original request, and findings that lack evidence.

Skill for Claude CodeCodex

Part of the quantum-loop plugin — 10 skills, 10 agents shipped together

Install

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.

agentmods
npx agentmods add skills/andyzengmath/quantum-loop/ql-deep-review
Any agent
npx skills add andyzengmath/quantum-loop --skill ql-deep-review
Clone the repo
git clone --depth 1 https://github.com/andyzengmath/quantum-loop

Made for: Claude Code, Codex.

Or install quantum-loop, the plugin that ships this one along with the rest of its 10 skills, 10 agents.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,668 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00079 $0.02668
Opus 5 $0.00039 $0.01334
Sonnet 5 $0.00016 $0.00534
Haiku 4.5 $0.00008 $0.00267

Measured 3d ago against content hash 93e986af54c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ql-deep-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 3d 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.

skills/ql-deep-review/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ql-deep-review — whole-feature post-implementation review

Purpose

quantum-loop's built-in two-stage review gate (ql-review: spec-compliance → code-quality) operates on ONE story at a time inside ONE worktree. It does not detect:

  1. Cross-story divergence (e.g., story A uses 'google' as a secret key while story B uses 'google-api-key' for the same constant).
  2. Post-merge regressions (test that was green in isolation breaks after integration).
  3. Drift from original user intent (paraphrase chain from intent → design → PRD → plan → code).
  4. Low-signal comments that look like findings but lack evidence (CRA actionability is 0.9-19.2% per Chowdhury 2604.03196; human baseline is ~60%).

ql-deep-review closes these gaps with a whole-feature review that runs AFTER all stories in a wave / feature pass the per-story gate.

When to use

  • After ql-execute emits COMPLETE for a wave and before merging the feature branch to master.
  • After cherry-picking or merging a foreign branch whose conflict-resolution changed semantics.
  • Manually, when suspicion of cross-story drift is high (e.g., follow-on work after a long autonomous run).

What it does NOT do

  • Does not replace the per-story two-stage gate. Run ql-review per story, then this.
  • Does not auto-fix findings. Produces a structured report; user or orchestrator drives action.
  • Does not block merge autonomously. Emits a verdict + confidence; user decides.

Risk scoring (0-100)

Risk factors and weights (inspired by soliton's risk-adaptive dispatch):

Factor Weight Measurement
Blast radius 25 count of files touched in wave × (max transitive callers of any touched symbol ÷ 100)
Change complexity 15 difftastic or cloc diff line count; tree-sitter function edit count
Sensitive paths 20 glob match: auth/, payment/, *.env*, *secret*, *password*, *token*
File size / scope 10 total LOC touched / number of files
AI-authored signal 10 git commit trailer Co-Authored-By: Claude, uniform-style heuristic
Test coverage gap 10 production files touched without corresponding test edits
Intent-drift signal 10 ql-intent-check CRITICAL findings count (optional input)

Read the full file on GitHub · 197 lines

Changes

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.

  1. 3d ago First seen · 197 lines · 79 tokens per session scan A 93e986af54c1

Subscribe to this mod's changes

ql-deep-review is a skill published in the GitHub repository andyzengmath/quantum-loop (24 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 2,668 once invoked, about $0.0004 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.

Related

Other skills, from other repositories