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/iwe-org/dev-workspace/implementnpx skills add iwe-org/dev-workspace --skill implementgit clone --depth 1 https://github.com/iwe-org/dev-workspaceWhat 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 | $0.00066 | $0.00751 |
| Opus 5 | $0.00033 | $0.00376 |
| Sonnet 5 | $0.00013 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
implement 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 yesterday.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement a plan
Coding happens as it always does; this skill adds the discipline that keeps the plan document true while it happens. The plan is the source of truth: the code follows it, and where reality wins an argument, the plan is updated — never silently outgrown.
Steps
- Select the plan. Infer from conversation; if ambiguous, list the plans
under
## Activeindata/plans.mdand ask (most recently created first). Announce: "Working on: — task N of M". No plan exists for what the user wants built? Stop and point at the plan skill. - Load the context. Read the full plan, the specs in its
## Spec changes, anddata/product.md## Constraintsand## Authoring rules— they bind the code you're about to write. - Check
## Depends on. Every prerequisite plan must carrystage: done; if one doesn't, say so and stop — building on an unshipped dependency is how two plans end up half-true. - Re-verify the anchors. The plan's
## Key referencesline numbers were true when written; re-locate each symbol in the current checkout before relying on it. If lines moved, update the anchor list and its "verified as of" date — that edit is part of this session's work. - Execute the next unchecked task. Follow its
**Files:**list; write the code; run the tests that cover this task. When the task's work is done and its tests pass, tick its- [ ]→- [x]in the plan doc andiwe normalize. - Write back deviations. If implementation reveals the
## Approach(or a task breakdown) is wrong, update the plan — amend the section, add or split tasks — before coding past the discrepancy, and tell the user what changed and why. - Stop at a clean boundary. After each task (or more, if the user asked for a longer run), report progress — "3/5 tasks, next: " — and stop. Blocked mid-task? Leave the box unchecked, describe the blocker, and stop there instead.
- Finish. When the last box ticks, run the plan's
## Verificationcommands, report the results, and suggest the verify skill for the full pre-ship check, then the ship skill.
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.
- yesterday First seen · 56 lines · 66 tokens per session scan A f8723adfb07d
implement is a skill published in the GitHub repository iwe-org/dev-workspace (5 stars, last pushed 23d ago), licensed MIT. It adds 66 tokens to every session and 751 once invoked, about $0.0003 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
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案(产品发布稿、公众号文章、邮件、README 等), 或用户反馈文字「AI 味太重」「不像人写的」时,加载本 Skill。.
curly-quote-sft
Skill "curly-quote-sft" from bojieli/ai-agent-book, covering 中文技术文档符号与引用规范, 何时加载, 符号定义, 决策优先级 and 正反例约束.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件,再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作,也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
research
用真实检索工具查找可追溯的事实、数据和来源。.