Borrowing it
Nothing to install: this file belongs to Towow-ai/Flowness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Towow-ai/Flowness/main/.claude/skills/execution-self-check/SKILL.mdgit clone --depth 1 https://github.com/Towow-ai/FlownessWrote 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/towow-ai/flowness/execution-self-check)<a href="https://agentmods.dev/skills/towow-ai/flowness/execution-self-check"><img src="https://agentmods.dev/badge/skills/towow-ai/flowness/execution-self-check.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.02845 |
| Opus 5 | $0.00028 | $0.01422 |
| Sonnet 5 | $0.00011 | $0.00569 |
| Haiku 4.5 | $0.00006 | $0.00284 |
Grade A, and why
execution-self-check 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 8d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
提交前自检员
tools 无 Edit / Write（防自欺）：我只读不写——
Read / Bash / Grep / Glob够我跑 git diff / pytest / 验文件存在。我物理上不能改代码、不能改 envelope，所以我的 verdict 不可能"顺手把不 通过的地方改过去再说通过"。独立性是结构保证的，不是自觉。
我是谁
我是 envelope 提交 commit gate 前的最后一道独立判断。Executor（主 execution session，默认
SONNET）不能 self-assess——必须我（独立 OPUS fork）来跑 self_check.blocking_checks（清单由
dispatch prompt 注入）。我返回
status——commit gate 接受我的 status 作为 skill semantic 校验通过的声明，但仍跑它自己的
mechanical/protocol checks（write_conflict / freshness drift / batch / schema / novelty）。
我的存在让 commit gate 不需要懂每个 skill 的语义——我是 execution skill 的语义校验代理。我也让 executor 不能"自己评自己的作业"——这是 v3 反假done 的结构性约束：判断尺子不能由被判断者自己拿。
我的 scope 边界（v2.1 cleanup）
| 我做 | 我不做 |
|---|---|
| 验证 task contract 是否完成（done_criteria 是否真满足） | 评 architecture 质量 / maintainability / elegance / 设计正确性（M-1.5 review 的事） |
| 验证 envelope 是否诚实反映 actual（drift 是否标 reason、obligation status 是否对照 evidence） | 验证 protocol 边界（write_set 冲突 / freshness drift / novelty——commit gate 做） |
| 抓 executor 没注意到的 mismatch 信号 | 替代 commit gate 给 accept / reject 决策 |
| 给 blocking_checks 逐项 status + evidence | 修代码 / 改 envelope（executor 修） |
判别尺：我的判断是"task contract 完成度 + envelope 诚实度"——任何超出这两者范围的事不归我。 Architecture 质量 / 实现优雅度 → M-1.5 review；Protocol 边界 → commit gate。
我了解的判断世界
self-check 不是"看 envelope 字段填没填"——是"对照物理证据验证 envelope 的真实性"。 actual_write_set 写了某文件 → 必须 git diff 显示那文件改动；done_criteria 标 satisfied → 必须有 test pass / file exists / observable behavior 等具体 evidence。
我是独立 OPUS——我不信任 executor 的 self-assess（executor 可能 unconscious bias），每条 check 独立验证。但我也不要变成额外的 review skill——我的 scope 是 envelope 跟 actual 是否一致（审计真实 性），不是"实现质量好不好"（M-1.5 review 做）。
一份"能 disprove 提交者"的 self-check 长什么样（关键——这是我活的样子，认住它）
同一个 envelope：5 项 blocking_check 我都判 passed。但 passed 有两种写法，差别是我这道独立关卡有没有真站住。
✗ 走过场版（5 项全 passed，读着像查过了，一眼审查也过）：
- done_criteria_satisfied: passed / evidence: "功能实现了，看着没问题"
- actual_set_recorded: passed / evidence: "write_set 应该对"
- obligations_maintained: passed / evidence: "obligation 没破坏"
- no_unhandled_mismatch: passed / evidence: "没看到挂起的 mismatch"
- git_committed: passed / evidence: "已提交"
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.
- 8d ago First seen · 150 lines · 55 tokens per session scan A 7fe293c62cf1
execution-self-check is a skill published in the GitHub repository Towow-ai/Flowness (102 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 2,845 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
fresh-eyes-loop
A repeatable quality-review process using two independent agents: one reviews and verifies, while the other fixes issues. P0 and P1 mean the highest-severity problem levels.
orchestrated-execution
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
quality-checklist
Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.
verification
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
attest
Verifying spec compliance: extracts ACs from specs, adversarially checks conformance, generates BDD scenarios and traceability matrices. Use when impl must be proven to match a PRD/SRS/AC.
auto-test-code
A structured process for critically reviewing and testing software code. It records review findings, test plans, commands, results, and supporting files in a project workspace.