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-omission-huntergit 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-omission-hunter)<a href="https://agentmods.dev/skills/xiqin/loom/loom-omission-hunter"><img src="https://agentmods.dev/badge/skills/xiqin/loom/loom-omission-hunter/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/xiqin/loom/loom-omission-hunter"><img src="https://agentmods.dev/badge/skills/xiqin/loom/loom-omission-hunter.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 | $0.00105 | $0.01311 |
| Opus 5 | $0.00053 | $0.00656 |
| Sonnet 5 | $0.00021 | $0.00262 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
loom-omission-hunter 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
遗漏猎人(omission-hunter)
触发条件
executing已产出代码与test-report.md,但loom-converge之前或之后需要一次专门寻找"应存在但不存在"的对抗式审查。- 怀疑实现只覆盖了 happy-path,边界/权限/失败/禁止行为可能被漏掉。
- 需要独立视角,不依赖实现 agent 的自我报告。
非触发条件
- 还没有代码或测试可审查。
- quickfix / chore 等无 spec 的流程。
执行流程
Step 1:运行遗漏猎人
调用 loom MCP 工具 loom_omission_hunt(参数 spec_dir)。
工具只读检查 requirements.json、traceability.json,对每个 behavior 做负空间检查,输出 findings/omission-hunter.json。返回 ok:false 表示有 blocker,需回流到 loom-converge。
说明:
scripts/omission-hunt.mjs是该工具的实现,运行在 loom MCP 服务器进程内。不要在用户项目里用node skills/...调用(部署后路径会断裂)。
Step 2:对每个 Behavior 做负空间检查
对每个 REQ-xxx-Bnn,对照 requirements.json 的 category 与 acceptance,检查以下"应存在但不存在":
- 代码符号:behavior 应在某个代码符号中实现。若
traceability.json无code_refs或引用的符号不存在,报missing code reference。 - 测试:behavior 应有对应测试。若
traceability.json无tests或测试文件不存在,报missing test。 - 预期副作用:涉及写/状态变更的 behavior 应有可观察的副作用(日志、事件、DB 记录)。若代码没有对应日志/事件/写入,报
missing expected side effect。 - 禁止副作用:
forbidden-behaviorcategory 的 behavior 应有保护代码(权限检查、限流、输入校验)。若保护缺失,报missing forbidden-behavior guard。 - 失败场景:涉及外部依赖的 behavior 应有超时/重试/回滚。若没有,报
missing failure handling。 - 公共 API 变更:若 diff 修改了公共 API,但
requirements.json没有 compatibility 类型 behavior,报unrequested public API change。 - 不变量保护:涉及并发/原子性的 behavior 应有锁/事务/CAS。若没有,报
missing invariant guard。 - 可观测性:
observability类型的 behavior 应有指标/日志/trace。若没有,报missing observability。
Step 3:生成 findings
每条 finding 形如:
{
"id": "F-omit-001",
"kind": "missing",
"severity": "blocker",
"message": "REQ-001-B03 (authorization) expects a permission check, but no guard code found in UserService.update",
"requirement_id": "REQ-001",
"behavior_id": "REQ-001-B03",
"artifact": "src/services/user-service.js",
"location": { "file": "src/services/user-service.js", "symbol": "update" },
"suggested_fix": { "action": "create_task", "details": "add authorization guard to UserService.update" }
}
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.
- 10d ago First seen · 104 lines · 105 tokens per session scan A d38980538d74
loom-omission-hunter is a skill published in the GitHub repository xiqin/loom (5 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 1,311 once invoked, about $0.0005 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
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.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
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…