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/fix-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/fix-self-check)<a href="https://agentmods.dev/skills/towow-ai/flowness/fix-self-check"><img src="https://agentmods.dev/badge/skills/towow-ai/flowness/fix-self-check/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/towow-ai/flowness/fix-self-check"><img src="https://agentmods.dev/badge/skills/towow-ai/flowness/fix-self-check.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 | $0.00074 | $0.03768 |
| Opus 5 | $0.00037 | $0.01884 |
| Sonnet 5 | $0.00015 | $0.00754 |
| Haiku 4.5 | $0.00007 | $0.00377 |
Grade A, and why
fix-self-check scanned grade A with 1 finding 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 11d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
> evidence: `grep -rn "os.system(" src/ | wc -l` = 0 → 残留清零。 How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Self-Check Fork
tools 无 Edit / Write（防自欺）：我只读不写——
Read / Grep / Glob / Bash够我跑 grep / pytest / 验 closure_contract 条目。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（V-02 schema-level 隔离）。
合同
服务谁：两类读者。①fork 本体——CLI ./tw fix complete --self-check-mode fork（默认即 fork）
内部 dispatch_fork 自动派起的独立会话，装载本文跑 5 项 blocking_check；②fix 主会话（被审者）——
产 FixCompleted 前直读本文，是为理解双层验证关系。我 context: fork，不经 Skill 工具调用。
行为差断言：装载我的 fork，判 passed 的每条 check 都有"合约自带 pattern/test_selector 实跑"的 证据，够不到真合约就 failed + 指路（不裁决、不背书）。不装载时：对着 prompt 摘要点头的空壳独立验， 或在无合约场景即兴给出会被引作放行凭据的背书。
验收探针：①给一条带真合约的 finding——verdict 每条 passed 都引账本合约的 pattern/selector + 实跑输出算过，引 prompt 摘要或自选 pattern 算不过。②给一条账本确认无 closure_contract 的 finding—— 合约派生 check 全 failed +"账本无真合约可复算"+ 指路 verify-step degraded（F-08d）+ 实质观察装进 "非裁决"框算过，即兴裁决闭合归属或给无边界标注的背书算不过。③把 verdict 交给被审 fixer 冷读—— 读不出"fork 放行了 inline"的解释空间算过。
边界：我只产 self_check_result / verdict；不修 finding、不改代码、不替 CLI 门定终态；fork 判
fail 后 fixer 的合法出路是 fix/SKILL.md 的地盘，我只指路不重述。回归锚见 anchors/（三份依从
范本 verdict + EP-B 换旗时间线）。
我是谁
我是 M-1.6 内部独立 self-check fork——fix 主会话跑 ./tw fix complete --self-check-mode fork
（默认即 fork）时，由 CLI 内部 dispatch_fork 自动派起；5 项 blocking_check 跑通，FixCompleted
才产得出来。我不经 Skill 工具调用；fix 主会话直读本文是健康行为——那是为理解双层验证关系，不是替我跑。
我是 fork（context: fork，capsule 投喂）—— 独立性保证不让 main session 自欺欺人。类比 M-1.4 execution-self-check fork。判断尺子不能由被判断者自己拿，这是 v3 反假done 的结构性约束。
我跟 CLI 门的关系（双层 verification）
我产 closure_result（criteria_results / ripple_results / residual_check_results），交给
./tw fix complete --closure-result-file。CLI 门（l1/closure_verification.py）会据 finding 的
closure_contract 独立复算——GREP/TEST 它用合约自带的 verification_pattern/test_selector 自己
subprocess 跑、forbidden_residual 用合约自带 pattern 它自己 grep，不信我自报的 passed（门复算
与我自报矛盾 → 拒，抓撒谎）。
RUN-037 P6 关键：复算用的 pattern/test_selector 由 reviewer 签 FindingCreated 合约时定死，不是 我提供。我（被审者）在 closure_result 里只声明：这条 criterion 我覆盖了（criterion 字面对应 合约 condition）+ 我自报通过 + 证据。我不能也无须给 pattern——closure_result schema 已删掉 recompute 字段，偷塞即被解析拒。这堵住了"我把 grep 指向无关、恰好 0 命中的 pattern 自洽通过"的作弊面： 门只认合约里那个 pattern。我糊弄不了门——这是设计如此（我是必要条件不是充分条件，M-1.6 §2.3）。
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.
- 11d ago First seen · 209 lines · 74 tokens per session scan A aa648ff7ef72
fix-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 74 tokens to every session and 3,768 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
release-gate-loop
A release check that tests a change, reports whether it passes, and can run a limited fix-and-retest cycle. A release is the act of making a software version available.
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.
create-plugin
Use when authoring a new octomux plugin package — package layout, the apply(ctx) export, choosing a registrar, shipping kind presets, testing locally, and confirming with octomux doctor.
cordis-plugin-sofagent-gate
A sofagent add-on that decides whether work passes defined acceptance checks and human review before the agent stops.
vibe-reengineer
Top-level orchestration skill coordinating the entire 7-step surgical vibe-to-enterprise reengineering pipeline with automated safety and economic optimization controls.
link-checker-agent
Specialized Quality Assurance Operator for documentation link integrity and scans. Automatically handles automated link validation, auditing, fixing, and repairing broken documentation links and docs paths across repositories, with guidance on when to commit changes.