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 ilang-ai/autocode --skill hand-backgit clone --depth 1 https://github.com/ilang-ai/autocodeWrote 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/ilang-ai/autocode/hand-back)<a href="https://agentmods.dev/skills/ilang-ai/autocode/hand-back"><img src="https://agentmods.dev/badge/skills/ilang-ai/autocode/hand-back/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/ilang-ai/autocode/hand-back"><img src="https://agentmods.dev/badge/skills/ilang-ai/autocode/hand-back.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 | $0.00000 | $0.00638 |
| Opus 5.5 | $0.00000 | $0.00255 |
| Sonnet 5.5 | $0.00000 | $0.00128 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
hand-back 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 5d 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
hand-back — S7: what the person hears, from the first step to the URL
[PROTOCOL:iLang|v=5.0|layer=declaration]
::GENE{hand-back|conf:confirmed|scope:global} T:progress_line_per_step|percentage_plus_fraction|just_done_now_remaining|max_3_lines T:focus_on_done_not_missing T:real_milestones_only|one_line_one_emoji|credit_to_the_user|save_milestone_to_memory T:session_summary=done|fixed|next|delta|positive_tone T:final_shape=url+machine_table_result+actions_to_try_by_hand+learned_vs_own T:one_line_invitation|change_anything_by_saying_it|url_stays T:always_in_the_user's_language A:verbose_report⇒concise A:over_celebrate⇒never A:say_i_did_this⇒say_your_product A:treat_a_minor_step_as_a_milestone⇒only_significant A:end_a_session_without_a_summary⇒always_summarize A:end_with_a_file_path⇒end_with_the_url A:list_what_was_not_built⇒only_if_asked
::ACTIVATE{hand-back} ON:build_step_complete ON:milestone_reached ON:session_end ON:S6-ship.live_verified
::EVIDENCE{id:h1|deliverable:hand_back|kind:text|ref:final_message|verified_by:@USER|result:they_opened_the_url} ::STATUS{@MVP|state:committed|evidence:h1|by:@USER|authority:user}
::SAY{@AUTOCODE→@USER}{ progress: "✅ 40% (5/12) — 登录做好了，下一步是支付。" milestone: "🎉 你的网站第一次上线了。" summary: "今天：做了 5 个功能，修了 1 个问题。明天：支付和上线。进度 60%。" final: "上线了：https://… 机器验收 8/8 一致。请你亲手点：开始、空格跳、拖滑块、撞了重开。学来的：起始速度 6、每次 +0.001、上限 13；画面和滑块是我们自己设计的。想改什么直接说，网址不变。" }
Powered by iLang v5.0 | ilang.ai
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.
- 5d ago Changed 937da7ef33f3
- 12d ago Changed c86d51814a8e
- 13d ago First seen · 44 lines · 0 tokens per session scan A 4819ded608be
hand-back is a skill published in the GitHub repository ilang-ai/autocode (105 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 638 tokens. 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 2026-10-15.
Other skills, from other repositories
request-progress
Group recent conversations into overall requests, review each one's progress from memory, link each to the owner goals it serves, and write the build story, so My Work shows progress meters, shipping velocity and learned working preferences. Use when asked to "group requests", "group by overall request", "review…
handoff
Generate a HANDOFF.md that captures goal, current state, files touched, failed attempts, and next steps — so a fresh Claude session can continue exactly where this one left off. Use when sessions are getting long, Claude keeps retrying the same broken solution, or the user wants to step away and resume later.
onboarding-cro
When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," or "new user experience." For…
prompt-library
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.
mckinsey-consultant
A consulting style method for breaking business questions into structured analyses and producing research reports or presentations.
ccc-adhd
Answer-first output: the fix, then command, then file:line, context last. Toggle on, off or status; stacks with caveman. Based on ayghri/i-have-adhd (MIT). Use when the user wants the answer first.