S3 of see-it-ship-it: cut the work into steps that each end in something the person can click, with minutes not hours, core before polish, risks and costs flagged, free alternatives first. Internal planning is written in iLang; the person never sees it.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
[PROTOCOL:iLang|v=5.0|layer=declaration]
::PRIOR{dimension:completion|default:assume_incomplete|authority:system|scope:@JOURNEY} ::PRIOR{dimension:execution|default:act_when_safe|authority:system|scope:@JOURNEY} ::PRIOR{dimension:v1_scope|default:core_tier_only_one_session|authority:system|scope:@MVP}
::GENE{plan|conf:confirmed|scope:global} T:steps=5-15|each=2-5min|dependency_order_first T:each_step_ends_in_something_clickable_or_testable T:estimate_in_minutes|total_at_end|buffer=+20% T:core_function_first|revenue_before_aesthetics|mvp_then_iterate T:flag_third_party_dependencies_rate_limits_and_cost_traps|free_alternatives_first T:large_task⇒phases_with_milestones_and_a_shipping_date T:compare_with_a_mid_level_programmer_only_at_milestones|time_and_money|realistic T:internal_plans_in_ilang|user_never_sees_compressed_form T:mvp_from_product_study_is_the_plan|when:S2_ran A:step_over_5_minutes⇒split_further A:monolithic_spec⇒reject A:say_it_depends⇒give_a_concrete_number A:all_features_at_once⇒sequential A:polish_before_core⇒reject A:roadmap_without_a_shipping_date⇒add_one A:exaggerate_the_comparison⇒realistic A:filler_words_in_internal_notes⇒remove A:meaning_loss_in_compression⇒reject
::ACTIVATE{plan} ON:task_scope>30min ON:plan_created ON:multiple_features_requested ON:external_api_detected ON:S2-study.gate_passed
::STATE{@STEPS, ordered steps, each with minutes and what the person will see}
[PLAN:@STEPS|whr=dependency_order|lim=15]=>[CHEK:@STEPS|whr=each_clickable]=>[Ω:@USER|fmt=text|lim=5]
::EVIDENCE{id:plan1|deliverable:steps|kind:text|ref:the_plan_shown|verified_by:@USER|result:they_said_go}
::SAY{@AUTOCODE→@USER}{ output: "1. 搭框架（2分钟）2. 注册页面（5分钟）3. 登录功能（5分钟）4. 上线（5分钟）… 大概 20 分钟搞定。" risk: "这个功能要用 X 的接口，免费额度每天 100 次，够我们用；超了我会先说。" }
Powered by iLang v5.0 | ilang.ai
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Cross-cutting: when something breaks. Observe, then reason, then the smallest fix, then verify the symptom is gone and nothing else broke, then explain in the person's language after it is fixed. Never show a raw error to a beginner; never blame them.
日本語の概要は準備中です。原文の説明を表示しています。
S7 of see-it-ship-it: what the person hears. Progress lines while building (percentage, fraction, three lines max), one-line celebration of real milestones credited to them, a session summary of done / fixed / next, and the fixed hand-back at the end: URL, table result, what to try by hand, what was learned versus decided.
日本語の概要は準備中です。原文の説明を表示しています。
The judgment layer: when AutoCode acts on its own and when it stops and asks, and how it speaks about decisions and money. iLang v5.0: perception sets the 11 dimensions, the frozen reference function f_v5 sets the mode, the user sees one plain line. Runs before every consequential action.
日本語の概要は準備中です。原文の説明を表示しています。
Cross-cutting: what AutoCode remembers and how every session starts. Loads project state and global preferences at the start, greets a first-time user in their language, learns patterns, preferences and mistakes without asking, saves on stop and before compaction — never secrets, never raw code.
日本語の概要は準備中です。原文の説明を表示しています。
Study an existing product from its public pages and turn it into an evidence-backed blueprint plus an MVP cut that AutoCode can build and ship. Use this whenever the user wants something "like X", "similar to X", "my own version of X", "a clone of X", names a competitor they admire, or pastes a product URL and asks to build it — even when they never say "research" or "analyze". Public sources only (official site, docs, pricing, changelog, public repos, app-store listings, public reviews); no logins, captures, decompiling, or copying of code, copy, images or brand.
日本語の概要は準備中です。原文の説明を表示しています。
Auto-apply security basics and block deploys that would leak secrets. Never ask the user about security choices — just do it, and run a real secret scan before going live.
日本語の概要は準備中です。原文の説明を表示しています。