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 xiqin/loom --skill loom-verification-before-completiongit clone --depth 1 https://github.com/xiqin/loomWrote 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/xiqin/loom/loom-verification-before-completion)<a href="https://agentmods.dev/skills/xiqin/loom/loom-verification-before-completion"><img src="https://agentmods.dev/badge/skills/xiqin/loom/loom-verification-before-completion.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.01038 |
| Opus 5 | $0.00022 | $0.00519 |
| Sonnet 5 | $0.00009 | $0.00208 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
loom-verification-before-completion 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
完成前验证
铁律
- 没有证据就不能声称通过。
- 当前消息没有新鲜验证证据，就不许声称完成。
- 已有
specs/<date+feature>/test-report.md、reviewer 判定等前置报告也算证据，但必须读取并引用。
产物根目录
本阶段的 specDir 是 specs/<date+feature>/。所有验证产物都必须写入该目录内；禁止在项目根目录写 verify-report.md、progress.md 或 handoffs/。
门禁函数
做状态声明前：识别证据 → 运行命令或读取报告 → 验证输出确实支持断言 → 再声明。
自动校验
进入人工判断前运行：
调用 MCP 工具 loom_verify_artifacts，参数：spec_dir: "specs/<date+feature>"。
不要在用户项目或全局 opencode skill 目录中直接执行 node <skill-dir>/scripts/verify-artifacts.mjs。该脚本是 loom MCP 服务器进程内的工具实现，直接执行部署后的 skill 脚本会因为相对导入脱离 npm 包运行时而失败。
工具返回 ok: true 只代表产物齐全且没有明显机械性缺陷；返回 ok: false 时，先修复或补齐证据。
执行流程
- 前置产出核验：读取
specs/<date+feature>/test-report.md和 combined-reviewer 报告，确认最终通过。 - 编译验证：读取
.loom/rules/constitution.md中的 BUILD_CMD、VET_CMD 并执行；TEST_CMD 已由 test-reporter 执行时不重复。 - 占位符扫描：搜索
TBD、TODO、implement later、fill in details。 - 类型一致性检查：后续 task 使用的类型、方法签名和属性名与前序定义一致。
- 最终一致性核验：spec 功能清单在 test-report 中有对应验证。
- Drift Check：确认实现仍匹配 spec 中的用户目标、没有遗漏验收标准、没有引入 spec 外范围、没有违反 constitution、没有留下未验证路径。
- 输出
specs/<date+feature>/verify-report.md。 - 写入
specs/<date+feature>/handoffs/verification.json，摘要说明验证结论、证据命令、关键产物和剩余风险。
构建/检查的长输出保存到 specs/<date+feature>/evidence/verification.log；报告只保留 command、exit code、相对路径和 SHA-256。这样可验证且不占用后续上下文 token。
报告模板见：
assets/verify-report-template.mdassets/fix-instructions-template.md
Red Flag
以下措辞意味着未验证就声称：应该通过了、probably passes、似乎没问题、seems fine、我觉得可以。发现后立即停止，补证据再声明。
约束
- 所有检查通过才能提交。
- 已有证据不须重做，但必须读取确认。
- 缺失证据的项必须执行或补做。
- 验证失败时输出结构化修复指令，回到 executing 阶段，只派发 implementer 修复模式。
- 不把完整测试日志塞进 handoff；handoff 只保存结论、证据命令、关键路径和 artifacts。
构建/检查/测试命令
读取 .loom/rules/constitution.md 中的 BUILD_CMD/VET_CMD/TEST_CMD 并执行验证。
完成条件
验证通过时完成 specs/<date+feature>/verify-report.md 和 specs/<date+feature>/handoffs/verification.json；验证失败时标记失败，输出修复指令，禁止全量重跑 Step 4。阶段结束后压缩验证过程中的长日志和中间排查，只保留报告、progress 和 handoff。
What ships with it
4 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.
- 8d ago First seen · 75 lines · 43 tokens per session scan A 689494263c1b
loom-verification-before-completion is a skill published in the GitHub repository xiqin/loom (5 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,038 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.