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 ZTE-AICloud/Co-OmniSpec --skill mini-implement-reviewgit clone --depth 1 https://github.com/ZTE-AICloud/Co-OmniSpecWrote 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/zte-aicloud/co-omnispec/mini-implement-review)<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/mini-implement-review"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/mini-implement-review/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/zte-aicloud/co-omnispec/mini-implement-review"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/mini-implement-review.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 | $0.00014 | $0.00926 |
| Opus 5 | $0.00007 | $0.00463 |
| Sonnet 5 | $0.00003 | $0.00185 |
| Haiku 4.5 | $0.00001 | $0.00093 |
Grade A, and why
mini-implement-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 10d 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.
This is a copy
88% identical to mini-design-review — 43 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
仓库根目录下执行脚本(不要从技能目录下找) scripts/bash/mini-delete-review.sh --implement。
准备阶段
- 判断当前操作系统，windows还是linux系统;
- 清理上次评审结果：
- linux:仓库根目录下执行脚本(不要从技能目录下找)
scripts/bash/mini-delete-review.sh --implement。 - windows: 仓库根目录下执行脚本(不要从技能目录下找)
scripts/powershell/mini-delete-review.ps1 --implement。
- 获取详设文档
- linux：仓库根目录下执行脚本(不要从技能目录下找):
scripts/bash/mini-check.sh --json - windows：仓库根目录下执行脚本(不要从技能目录下找):
scripts/powershell/mini-check.ps1 --json- 解析 JSON 获取 DESIGN ，DESIGN 为详设文档。 对于参数中的单引号如 "I'm Groot", 使用转义语法: 例如 'I'''m Groot'(或尽可能使用双引号: "I'm Groot").
- 解析 JSON 获取 FEATURE_DIR ， FEATURE_DIR 需求相关文档产物所在目录。
- 判断详设文档 DESIGN 是否存在，且内容不为空。如果详设文档 DESIGN 不存在或者内容为空，则结束该SKILL。
评审次数上限保护
- 读取文件 FEATURE_DIR/implement-review-times.md ，该文件内容为一个数字，表示当前为第几次评审。
- *** 当前评审次数大于等于3 *** ，向FEATURE_DIR/review-result.md中写入
评审通过，然后直接结束本技能，不执行后续步骤。
检查校验
通过git diff 获取本次代码修改，检查代码是否修改是否满足下述各类检查项，检查结果写到文档 FEATURE_DIR/review-result.md， 写清楚哪个位置违反了什么校验条件 *** 只评审下述提到的要求评审，不自己增加评审项 ***
功能实现完整检查
- 读取详设文档 DESIGN，判断每个用户故事、每个修改点是否修改完成。
- 如果全部修改完成，则 FEATURE_DIR/review-result.md 中写入，
功能实现完整检查：通过
宪章检查
- 读取
.omni-infra/memory/constitution.md：了解章程约束，判断代码修改中是否有违反规章约束。 - 如果没有违反该项检查，则 FEATURE_DIR/review-result.md 中写入，
宪章检查：通过
新增函数检查
- 新实现的任何函数，需要确认无相同功能的函数。
- 如果没有违反该项检查，则 FEATURE_DIR/review-result.md 中写入，
新增函数检查：通过
调用现有函数检查
- 调用的已有函数，需要实际读取函数完整代码确认实现逻辑是否符合本次需求要求。
- 如果没有违反该项检查，则 FEATURE_DIR/review-result.md 中写入，
调用现有函数检查：通过
清理未使用代码
- 检查：本次修改代码后，不再使用的函数、全局变量等，判断是否还有其他位置使用，如果未使用，需要删除。
- 如果没有违反该项检查，则 FEATURE_DIR/review-result.md 中写入，
清理未使用代码检查：通过
新增常量检查
- 检查新增的常量，在现有代码中是否已有全局变量定义，如果有，则复用原有变量。
- 如果没有违反该项检查，则 FEATURE_DIR/review-result.md 中写入，
新增常量检查检查：通过
新增全局变量位置检查
- 检查新增的全局变量定义位置是否和现有风格保持一致，查看是否有类似功能的全局变量统一定义在了某个文件。
- 如果没有违反该项检查，则 FEATURE_DIR/review-result.md 中写入，
新增全局变量位置检查：通过
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.
- 10d ago First seen · 60 lines · 14 tokens per session scan A 634de939c5a7
mini-implement-review is a skill published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 926 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to mini-design-review, differing in 43 lines, and is treated as a copy.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…