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 agentmods add skills/stepanenkoviktor0110-boop/ai-dev-methodology/write-codenpx skills add stepanenkoviktor0110-boop/ai-dev-methodology --skill write-codegit clone --depth 1 https://github.com/stepanenkoviktor0110-boop/ai-dev-methodologyWrote 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/stepanenkoviktor0110-boop/ai-dev-methodology/write-code)<a href="https://agentmods.dev/skills/stepanenkoviktor0110-boop/ai-dev-methodology/write-code"><img src="https://agentmods.dev/badge/skills/stepanenkoviktor0110-boop/ai-dev-methodology/write-code.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 | $0.00016 | $0.00038 |
| Opus 5 | $0.00008 | $0.00019 |
| Sonnet 5 | $0.00003 | $0.00008 |
| Haiku 4.5 | $0.00002 | $0.00004 |
Grade A, and why
write-code 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 today.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- today First seen · 10 lines · 16 tokens per session scan A 7c20e39216e3
write-code is a skill published in the GitHub repository stepanenkoviktor0110-boop/ai-dev-methodology (2 stars, last pushed 10d ago), with no licence file. It adds 16 tokens to every session and 38 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
doc-layer-system
AI 驱动开发七层文档体系的可执行通用 skill。在任何涉及代码开发、文档同步、代码审查、测试编写的任务中，Agent 必须遵循此体系的分层规则、授权角色裁决规则、同步流程和变更钩子机制。项目特定规则（目录路径、治理角色、域列表、死亡线区域清单、金标准领域清单等）通过项目级 skill 补丁扩展，本 skill 不硬编码任何项目特定内容。触发场景：编写/修改代码或文档后需要同步、新增接口/数据库/页面功能、执行 /review、编写测试用例、处理文档与代码之间的矛盾、询问「这个东西该放哪里」或「这几个文档矛盾了听谁的」。.
goal-charter
为规格已冻结的施工编写 goal 执行章程，锁定目标、验证器、边界、自愈清单和启动参数。触发：写 goal 章程、定义自主执行边界、把施工/提交/部署/测试交给 goal 闭环。设计用 lightweight-design，用例用 test-case-design，总控用 task-control-doc。.
lightweight-design
轻量设计方案 skill（用户级通用）。把局部改造/开发任务里的高风险决策在动工前清算钉死，并产出事实基线、最终任务真值切片、规范条目索引 SD-x、业务主题唯一性账 TOPIC-x、影响面与 SD→正式规格→AC 追溯关系，保证全部有效设计语义零遗漏物化到七层且同一问题在全部正式层只有一个答案。施工切片归 goal-charter，对抗评审归 adversarial-review，实现细节不进文档。.
code-to-7layer
从现有代码证据冷启动、生成七层文档反推总控文档的 skill（用户级通用）。代码只用于发现现状与候选规格，不取得正式文档裁决权。本 skill 交付「扫描摘要 + 任务总控编排文档」，不直接撰写具体层文档；Phase 3 由 /control 驱动。适用场景：项目无文档或文档严重过时、需要系统性规划七层文档补写任务。触发词：「冷启动建文档骨架」「反推文档体系总控」「从代码反推文档」「代码到七层」「反推文档体系」。.
codex-review
仅手动触发。施工完成后，用 Codex GPT-5.5 对照冻结的 L1–L7、规格物化报告、goal 章程和工程红线做单模型符合性核验；不挂门禁，不替代高风险多视角审查。.
legacy-archaeology
从老旧黑盒代码反推「树形索引、逐层下钻」的知识库（业务逻辑/数据库/接口三层），给重构 AI 注入背景。承诺「边界内可审计覆盖 + 残余风险显式登记」，不承诺零遗漏。触发词：「老代码考古」「反推知识库」「重构前背景」「把老项目翻译成文档」「legacy 调查」。.