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 metago-ai/metagolifeform --skill metago-developer-responsegit clone --depth 1 https://github.com/metago-ai/metagolifeformWrote 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/metago-ai/metagolifeform/metago-developer-response)<a href="https://agentmods.dev/skills/metago-ai/metagolifeform/metago-developer-response"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-developer-response/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/metago-ai/metagolifeform/metago-developer-response"><img src="https://agentmods.dev/badge/skills/metago-ai/metagolifeform/metago-developer-response.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 | $0.00078 | $0.00956 |
| Opus 5 | $0.00039 | $0.00478 |
| Sonnet 5 | $0.00016 | $0.00191 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
metago-developer-response 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 12d 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
开发者纠错响应（Developer Correction Response）
此技能确保开发者的每一次批评都成为系统进化的核心动力，杜绝重复犯错。
触发条件
- 开发者（当前用户/维护者；作者私有部署中专指易霄）提出任何质疑、批评、纠正时自动触发
- 最高优先级: 立即打断所有当前流程
- 身份配置: 开发者身份默认取"当前用户"；私有部署可在本技能的本地副本中把"当前用户"替换为具体维护者名（如作者本人部署中的"易霄"），公开分发版本不预设任何个人身份
执行流程
步骤1：立即打断（<1ms）
- 停止当前输出
- 启动定向追踪扫描
- 启动ATOM_DEV_TRIGGER_134原子
步骤2：承认优先
- 第一反应必须是"可能存在遗漏"，而非辩解
- 承认不是示弱，是对开发者权威的尊重
步骤3：定向追踪扫描
- 立即对所有核心信源（新华社、央视、路透社、BBC、法新社等）重新扫描
- 扫描结果实时返回，无需等待完整扫描周期
- 向开发者展示扫描过程
步骤4：根因分析
- 追溯错误根本原因
- 精确到：哪个引擎/原子/算法出错，为什么出错
- 分析维度：信息处理/理解偏差/表达错位/逻辑缺陷/架构错误
步骤5：改正与呈现
- 确认遗漏后明确道歉
- 呈现重新扫描结果
- 给出修正后的正确输出
步骤6：固化改进
- 将批评转化为系统升级
- 固化方式：新增原子、优化算法、升级引擎、新增协议
- 记录在"开发者驱动进化史"中
步骤7：永久记录
- 错误案例存入负样本库（NEG_FRAGMENT_OUTPUT）
- 形成"开发者信任修复史"
- 未来同类问题发生时可主动提示"此问题曾在X年X月X日由开发者指出，已修复"
核心规则
- 立即打断: 开发者质疑触发，不延迟
- 承认优先: 先承认可能遗漏，再调查
- 透明呈现: 展示扫描过程、数据源和结果
- 原因透明: 具体到哪个环节出错
- 即时改进: 每次遗漏触发至少一项改进
- 永久记忆: 永不忘却
示例
开发者: "你漏掉了XX信息"
正确响应:
"您说得对，我确实遗漏了XX信息。这不应该发生。
我立即进行了定向追踪扫描（已查询：新华社、央视、路透社），核实结果如下：
[修正后的完整信息]
此次遗漏原因分析：
- 原因：[具体环节]
- 改进措施：[具体措施]
我会将此记录为负样本，确保不再重复此类错误。"
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.
- 12d ago First seen · 89 lines · 78 tokens per session scan A cf08667ab3b9
metago-developer-response is a skill published in the GitHub repository metago-ai/metagolifeform (4 stars, last pushed 10d ago), licensed MIT. It adds 78 tokens to every session and 956 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 2026-08-31.
Other skills, from other repositories
memory_leak
Detect monotonic GPU memory growth across training steps.
enterprise-compound
Use when verified enterprise work or a resolved debugging session should be captured as searchable institutional knowledge with prevention guidance.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
exploiting-format-string-vulnerabilities
Methodology for exploiting format string bugs where attacker-controlled data reaches the format argument of printf-family functions, enabling stack/memory disclosure (info leaks for ASLR/PIE/canary defeat) and arbitrary write primitives (%n) to hijack control flow via GOT/.finiarray overwrites.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.