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-convergegit 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-converge)<a href="https://agentmods.dev/skills/xiqin/loom/loom-converge"><img src="https://agentmods.dev/badge/skills/xiqin/loom/loom-converge/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-converge"><img src="https://agentmods.dev/badge/skills/xiqin/loom/loom-converge.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 | $0.00094 | $0.01432 |
| Opus 5 | $0.00047 | $0.00716 |
| Sonnet 5 | $0.00019 | $0.00286 |
| Haiku 4.5 | $0.00009 | $0.00143 |
Grade A, and why
loom-converge 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
收敛(converge)
触发条件
executing阶段已产出test-report.md且 verdict 为 PASS。- 即将进入
verification,但尚未把代码事实对照意图清单做收敛。 requirements.json与traceability.json存在。
非触发条件
test-report.md仍为 FAIL 或未产出。- quickfix / chore 等无 spec 的流程。
执行流程
Step 1:运行收敛
调用 loom MCP 工具 loom_converge(参数 spec_dir、round)。
工具读取 requirements.json、traceability.json,对每个 behavior 分类为 covered/missing/partial/contradicts/unrequested,输出 convergence-report.json。返回 ok:false 表示有 blocker(missing/contradicts),需要回流 executing。
说明:
scripts/converge.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:逐 behavior 分类
对每个 REQ-xxx-Bnn behavior,依据 traceability.json 的 tests/evidence 与实际代码/测试文件,分类为:
covered:tests 引用真实存在的测试文件,且 evidence 引用真实日志,且 behavior 的 acceptance 被测试覆盖。missing:traceability 中无 tests 或 evidence,或引用文件不存在。partial:有 tests 但未覆盖 acceptance 全部分支(例如只测 happy-path,未测 invalid-input)。contradicts:实现与 spec/requirements 描述冲突,或测试断言与 acceptance 相反。unrequested:代码中实现了requirements.json没有声明的行为或公开 API 变更。
Step 3:生成 findings
每个 missing / partial / contradicts / unrequested 生成一条 finding:
{
"id": "F-conv-001",
"kind": "missing",
"severity": "blocker",
"message": "REQ-001-B03 (authorization) has no test reference in traceability.json",
"requirement_id": "REQ-001",
"behavior_id": "REQ-001-B03",
"artifact": "traceability.json",
"suggested_fix": { "action": "create_task", "details": "add task T2 to implement authorization test for REQ-001-B03" }
}
Step 4:追加新 task 回流
对所有 missing / partial / contradicts,生成新 task 文件 tasks/T*.md,frontmatter 包含:
requirements: 对应REQ-xxxbehavior_ids: 对应REQ-xxx-Bnnowns: 建议修改的文件(从 finding 的 location 或现有代码推断)depends_on: 依赖的原 task
把新 task 追加到 plan.md 的 task 表。更新 traceability.json 把新 task 加入对应 behavior 的 tasks。
Step 5:更新 convergence-report.json
{
"stage": "converge",
"round": 1,
"status": "converged|needs_another_round",
"classification": {
"REQ-001-B01": "covered",
"REQ-001-B02": "covered",
"REQ-001-B03": "missing"
},
"findings": ["..."],
"new_tasks": ["T2", "T3"],
"coverage": {
"behavior_coverage": "67%",
"acceptance_coverage": "55%"
},
"created_at": "2026-07-20T18:30:00Z"
}
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 · 125 lines · 94 tokens per session scan A 171fd1f39e06
loom-converge is a skill published in the GitHub repository xiqin/loom (5 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,432 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
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.