Borrowing it
Nothing to install: this file belongs to Peiiii/nextclaw. 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/Peiiii/nextclaw/master/.agents/skills/iterative-quality-convergence/SKILL.mdgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/iterative-quality-convergence)<a href="https://agentmods.dev/skills/peiiii/nextclaw/iterative-quality-convergence"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/iterative-quality-convergence/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/peiiii/nextclaw/iterative-quality-convergence"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/iterative-quality-convergence.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 | $0.00079 | $0.00847 |
| Opus 5 | $0.00039 | $0.00424 |
| Sonnet 5 | $0.00016 | $0.00169 |
| Haiku 4.5 | $0.00008 | $0.00085 |
Grade A, and why
iterative-quality-convergence 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 9d 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.
What it actually says
迭代质量收敛
定位
探索“AI 能否像高标准的人类开发者一样，看到结果仍不够好时主动继续改进”。这是独立的探索性工作模式，不是新的生命周期阶段，也不以增加修改轮数为目标。
高质量不能由 AI 的主观满意证明。必须先建立任务特定标准，再观察真实产物、识别差距、执行最小改进并重新观察。
大型、多阶段任务若已有 acceptance-contract-governance 产出的验收契约，直接把其中的必须项、代表性场景和阶段门作为质量模型输入；本 skill 不另建一套完成标准。
进入条件
开始前确认：
- 目标、目标用户、成功条件、非目标和禁止边界；
- 当前可运行、可渲染、可读取或可比较的真实产物；
- 能证明质量变化的观察入口、参考标准或指标；
- 时间、风险或迭代预算，以及必须交给用户判断的偏好。
无法观察真实结果时不得假装收敛；先补观察条件，或明确停止。
建立质量模型
只选择当前任务最重要的三至五个维度，并为每个维度写出可观察标准。候选维度包括：
- 功能与状态行为是否正确；
- 用户任务是否顺畅、清晰且完整；
- 真实数据、边界状态和不同环境下是否仍成立；
- 信息、视觉、交互或内容是否一致并达到参考水平；
- 实现是否保持单一路径、清晰 owner 和必要复杂度；
- 结果是否真正增强预期用户价值。
不要用一个伪精确总分覆盖不同性质的差距。审美偏好、产品选择和技术正确性分别判断。
收敛循环
- 从用户或调用方视角运行、渲染或使用真实产物，记录可复查证据。
- 对照目标、质量模型、产品愿景和适用参考，列出具体差距。
- 区分缺陷、范围内质量改进、主观偏好和新需求；新需求不得借优化循环扩张进入当前任务。
- 选择当前影响最大、证据最强且能独立验证的一项差距。
- 执行最小改进，遵守项目已有的实现、验证和 Review 合同。
- 用同一观察入口重新评估，确认差距真实缩小且没有引入更大回归。
- 更新剩余差距并继续；没有显著改进价值时停止，不为证明“有循环”制造无意义修改。
每轮只追一个最大差距。若结果暴露目标或方案错误，回到正确的任务判断，而不是用局部润色掩盖。
停止条件
满足任一条件时停止：
- 所有必需维度达到明确标准，且没有仍值得处理的高价值差距；
- 下一轮预期收益低于实现、验证或回归成本；
- 需要用户偏好、产品方向、范围扩张或高风险授权；
- 达到约定预算，或真实环境无法继续观察。
最终输出质量标准、各轮最大差距与改进证据、停止原因、仍需用户判断的偏好和残余风险。不得只用“看起来不错”“测试通过”或“没有 finding”宣称达到高标准。
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.
- 9d ago First seen · 62 lines · 79 tokens per session scan A c2715f80d5c7
iterative-quality-convergence is a skill published in the GitHub repository Peiiii/nextclaw (256 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 847 once invoked, about $0.0004 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
openclaw-github-dedupe
Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.
tmux-lane-orchestrator
Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.
ghcrawl-cluster-operator
Use when inspecting a ghcrawl SQLite store, pulling GitHub issue/PR data, refreshing summaries, embeddings, and clusters, or extracting one cluster and its evidence through the ghcrawl CLI.
opik-optimizer
Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.
crabpot-perf-metrics
Interpret Crabpot and OpenClaw performance dashboard metrics, import-loop profiles, runtime profiles, and branch-to-branch perf deltas without over-reading noisy samples.
org-branch-cleanup
Audit and safely prune stale branches across a GitHub organization with immutable snapshots, conservative merged-PR classification, live SHA/protection/open-PR revalidation, resumable deletion ledgers, and post-delete verification. Use when a maintainer asks to clean up old, dead, merged, bot-created, or abandoned…