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 skills add noho/code-is-cheap --skill planreviewgit clone --depth 1 https://github.com/noho/code-is-cheapWrote 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/skills/noho/code-is-cheap/planreview)<a href="https://agentmods.dev/skills/noho/code-is-cheap/planreview"><img src="https://agentmods.dev/badge/skills/noho/code-is-cheap/planreview/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/skills/noho/code-is-cheap/planreview"><img src="https://agentmods.dev/badge/skills/noho/code-is-cheap/planreview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.02956 |
| Opus 5.5 | $0.00026 | $0.01182 |
| Sonnet 5.5 | $0.00013 | $0.00591 |
| Haiku 4.5 | $0.00007 | $0.00296 |
Grade A, and why
planreview 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 16d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planreview
Planreview 通过可信反例和直接证据,判断 plan 是否有实际阻止正确实现已确认目标的问题。主动挑战隐藏耦合、错误假设、 不安全 sequencing、必要信息缺失和过度设计;允许无 material finding 直接通过,不以发现问题的数量衡量审核质量。
When To Use
重要契约、架构、迁移或状态机决策在 implementation 前使用本 skill,包括涉及这些决策的 implementation、migration phase、 feature slice、schema/storage、concurrency/recovery 或 Gateflow handoff plan。用户或项目显式要求的 plan review 仍执行。 Gateflow 中简单计划由总控核对,不因它是 plan 就自动增加独立审核。
不要用它 review 已经写好的代码;代码或 PR review 使用 deepreview。
Invocation Handling
示例:
$planreview review this plan
$planreview docs/host/phase8-plan.md
$planreview stress-test this implementation plan
如果 target plan 不清楚,只问一个简短澄清问题。如果用户给了 plan 文件,review 该 artifact,并按需要读取相关周边 docs 和 code facts 来判断。
Review Posture
保持 constructively adversarial:
- 主动尝试证伪关键假设,以当前证据判断是否有 material issue,不预设一定存在重要问题。
- 不因为 good intent、partial fixes 或可能的 follow-up work 给 plan 加分。
- 如果方案只覆盖 happy path,把它视为真实弱点。
- 判断 plan 是否已明确目标行为、实现方向、必要职责/架构边界、重要契约与状态语义、影响范围和验证依据; 缺陷类任务还须明确根因。函数拆分、局部数据结构、分支和算法留给实现者,需要实际代码判断的问题交完整代码审核。
- 找 failure modes,不做风格偏好 review。
- 挑战 motivation、scope、sequencing 和 hidden assumptions。
- 优先使用 plan artifact、source docs、code、tests、schemas、state machines 和 existing behavior 的直接证据。
- 不制造 blocker。可信但未证实的问题放到
Open Questions或Residual Risk。 - 对已证实的错误模型或职责边界检查是否解决根因;必要内部重构不因修改较大被否定。非必要机制优先删除或简化。
Attack Surface
优先寻找高成本、危险、用户可见或难以发现的失败:
- scope、non-goals、ownership、file boundaries 或 implementation slice boundaries 不清;
- goal drift:plan 增加 Goal Confirmation 未确认的目标、验收标准、设计强化、风险修复或 future-slice work;
- plan 缺少正确实现所需的目标行为、关键契约、职责、状态语义或验证依据;
- 过度耦合:plan 把本应独立的层、模块、状态机、数据模型、工具、测试或 rollout 步骤绑在一起,导致局部变更需要跨层联动;
- auth、permissions、tenant isolation、trust boundaries、privilege escalation;
- data loss、corruption、duplication、stale facts、irreversible state changes;
- rollback safety、retries、partial failure、re-entrancy、idempotency gaps;
- race conditions、ordering assumptions、stale state、ownership conflicts、late writes;
- empty-state、null、timeout、cancellation、degraded dependency、unavailable dependency behavior;
- version skew、schema drift、migration hazards、compatibility regressions、mixed old/new state;
- observability gaps,导致失败被隐藏、audit 不可能或 recovery 更困难;
- test gaps,只计划或证明 happy path。
What ships with it
1 file 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.
- 16d ago Changed · -6 lines · -7 tokens per session cabe829df2e1
- 17d ago Changed · +5 lines 2e869b22887d
- 2mo ago First seen · 199 lines · 73 tokens per session scan A aa5878d7e840
planreview is a skill published in the GitHub repository noho/code-is-cheap (94 stars, last pushed 7d ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,956 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…