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.
git clone --depth 1 https://github.com/ayukyo/icode-skillWrote 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/commands/ayukyo/icode-skill/icode)<a href="https://agentmods.dev/commands/ayukyo/icode-skill/icode"><img src="https://agentmods.dev/badge/commands/ayukyo/icode-skill/icode/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/commands/ayukyo/icode-skill/icode"><img src="https://agentmods.dev/badge/commands/ayukyo/icode-skill/icode.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 | $0.00061 | $0.00406 |
| Opus 5.5 | $0.00024 | $0.00162 |
| Sonnet 5.5 | $0.00012 | $0.00081 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
icode scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
按 ICODE 端到端编码工作流处理本次请求。
用户输入：$ARGUMENTS
执行要求：
- 若本会话尚未加载 ICODE 技能，先加载
icodeskill；CodeBuddy 默认从~/.claude/skills/icode/SKILL.md读取它，并以此作为唯一路由入口。 - 保留完整用户输入、否定条件和工单上下文。明确子命令按原路由；自然语言或混合描述先读技能中的
references/natural_language_entry.md再选步骤，不能只按关键词猜。空输入或 help 只展示帮助，能力咨询不执行；/icode ui使用 ICODE 的 UI 默认入口。 - 严格按 SKILL.md 与
steps/目录下对应步骤文件执行；执行步骤前必须先读取对应步骤文件。help 按上述入口参考文档提供帮助，不虚构 help 步骤文件。 - 正式工单产物写入当前工程的
.icode_output/.icode_output_N/；状态与事件一律经python3 ~/.claude/skills/icode/tools/icode_control.py控制面执行，禁止绕过控制面直写 metadata。crosscheck是非工单例外：仅写.icode_output/.crosscheck/，不得写目标工单或代码。 - 遵守 Git 安全规则：禁止自动执行
git commit、git push及危险操作。 - 对用户的回复一律使用中文。
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.
- 25d ago Changed · -21 tokens per session 29530cb97bd5
- 29d ago Changed · +2 tokens per session c88166a3abcd
- 1mo ago Changed · +3 tokens per session c4145470e7bf
- 1mo ago First seen · 18 lines · 77 tokens per session scan A d721b3ad0574
icode is a command published in the GitHub repository ayukyo/icode-skill (4 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 406 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-14.
Other commands, from other repositories
handoff
Emit a handoff artifact for this session (optionally specify a slug).
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.
hatch3r-pr-resolve
Read open PR comments, evaluate each against current code via the rigor contract, implement accepted findings, reply inline. Multi-platform.
commit
Create a git commit using the Haiku model.
simplify-transform
Apply verified simplifications with user approval. Part of simplify- family.