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/qingye-lab/rootloom/operating-code-reviewnpx skills add qingye-lab/rootloom --skill operating-code-reviewgit clone --depth 1 https://github.com/qingye-lab/rootloomWhat 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 | $0.00045 | $0.00607 |
| Opus 5 | $0.00023 | $0.00303 |
| Sonnet 5 | $0.00009 | $0.00121 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
operating-code-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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code review
Review only. Do not modify code unless the user explicitly changes the task.
Scope
Read the requested diff plus the smallest sufficient callers, consumers, contracts, tests, configuration, schemas, generated behavior, and one analogous sibling. Treat the author's explanation and previous findings as leads, not proof.
Load specialized References only when Diff Facts require them:
- auth, trust boundaries, secrets, injection, or unsafe parsing: security-review.md;
- migrations, DDL, ORM models, persistent serialization, or stored formats: data-and-migration-review.md;
- manifests, lockfiles, packaging, CI, deployment, or release changes: dependency-and-release-review.md;
- formal UI, interaction, accessibility, responsive, or visual changes: ui-review.md.
Finding standard
A finding must include:
- severity: Critical, High, Medium, or Low;
- exact file and line/symbol;
- failure mode and triggering conditions;
- evidence from a code path, contract mismatch, reproduction, or missing durable test;
- the smallest concrete correction;
- confidence: verified, strongly inferred, or uncertain.
Do not report style preferences as defects. Separate questions and optional improvements from findings.
Review method
Start from the failure surface and trace ownership, callers, and consumers. Read the full relevant diff. Compare it with source-of-truth schemas, manifests, docs, CI, and tests. Attempt to disprove the strongest completion claim and test negative paths, cleanup, retries, cancellation, timeouts, partial failure, and mixed versions as applicable.
A guard, flag, journal, abstraction, or workflow step earns its place only when the review can name the observable failure, owning boundary, executable enforcement, regression proof, and decision it changes.
For a defect repair, require:
ROOT_CAUSE_ALIGNMENT: PASS | FAIL | NOT_APPLICABLE
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 72 lines · 45 tokens per session scan A 9da19fe3eded
operating-code-review is a skill published in the GitHub repository qingye-lab/rootloom (7 stars, last pushed 20d ago), licensed MIT. It adds 45 tokens to every session and 607 once invoked, about $0.0002 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 skills, from other repositories
audit-onboarding-proposal
Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…
improve-harness
Run one explicitly authorized, evidence-backed improvement to a repository's agent guidance, tools, runbooks, or validation. Use only when the user invokes $improve-harness or explicitly asks to improve the Harness after observed reusable agent friction. Do not use for ordinary product changes, speculative cleanup…
ai-elements
Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
product-decision-agent
中文产品决策 Agent。用于中国大陆互联网产品、运营、增长、商业化、数据、项目推进和组织协作场景：产品规划、需求分析、PRD、需求优先级、排期、版本规划、Roadmap、MVP、灰度、上线、迭代、增长停滞、拉新、投放、渠道、裂变、CAC、LTV、ROI、留存、转化、DAU/MAU、GMV、漏斗、社区运营、内容供给、创作者、用户运营、活动运营、私域、会员、定价、指标异常、数据口径、埋点、A/B…
architecture-review
Use for clean architecture, modular monoliths, hexagonal boundaries, service boundaries, data flow, dependency direction, ADRs, or large feature planning.