@akinet/akidevrule 3.3.0 → 3.4.0

package/skills/akidevsync-notes/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: akidevsync-notes
-description: Read and edit a project's `.akidevsync/notes.json` task/note file — the per-project task list written by the Aki-Dev-Sync app (github.com/lacvietanh/aki-dev-sync). Use when the user asks to list, add, pin/unpin, mark done, edit, or delete a task in that file, or mentions "task note", "note ghim", "pin task", "mark done", "notes.json", "akidevsync task". Also use when asked to cross-check pinned/open notes against what a release actually shipped (CHANGELOG, code) before marking them done.
+description: Read and edit a project's `.akidevsync/notes.json` task/note file — the per-project task list written by the Aki-Dev-Sync app (github.com/lacvietanh/aki-dev-sync). Use whenever the task reads or changes that project task list — listing, adding, pinning, completing, editing or deleting a task or note, in any wording. Also use when asked to cross-check pinned/open notes against what a release actually shipped (CHANGELOG, code) before marking them done.
 ---
 
 # akidevsync-notes — edit a project's Aki-Dev-Sync task file safely

package/skills/akiflow/references/harness-facts.md

@@ -8,6 +8,8 @@ The skill's rules are consequences of these facts. If a fact changes, the rule i
 
 Every entry carries the date it was checked, because all of it is version-bound and expected to rot.
 
+**CRITICAL — this file is facts, not policy: update it the moment a provider ships or retires a model, changes a flag, or a probe contradicts an entry.** Every model id below is a live default that other files quote by reference (`agent.A5`, `claude/agents/aki-hands.md`, `docs/arch/akiflow.md`); a stale id here is silently wrong everywhere. Never ask the owner whether to record an observed fact — record it, date it, and re-point the default when a newer tier of the same family is present (`agy models`, `claude --help`, `kiro-cli`).
+
 ## Worker invocation quick-facts
 
 The lookup table: literal command, read-only mechanism, and the one silent failure each lane hides. Every section below this one is the *why* — a caller assigning a lane needs none of it.
@@ -16,7 +18,7 @@ The lookup table: literal command, read-only mechanism, and the one silent failu
 
 | Lane | Literal command | Read-only by | Silent failure to check |
 |---|---|---|---|
-| **agy flash** — discovery default | `agy --model gemini-3.7-flash-high --mode plan --output-format json -p "<prompt>"` | `--mode plan` (mechanism, not wording) | a denied call still returns `status: "SUCCESS"` with empty `response`; `-p` takes the next token as its value, so any flag written after it is sent as prompt text |
+| **agy flash** — discovery default | `agy --model gemini-3.8-flash-high --mode plan --output-format json -p "<prompt>"` | `--mode plan` (mechanism, not wording) | a denied call still returns `status: "SUCCESS"` with empty `response`; `-p` takes the next token as its value, so any flag written after it is sent as prompt text |
 | **kiro-cli** | `kiro-cli chat --no-interactive --trust-tools=fs_read --model claude-sonnet-4.5 --effort high "<prompt>"` | `--trust-tools=fs_read` | none recorded; `--effort` is operative on every Kiro model, unlike `claude` + haiku |
 | **claude via proxy gateway** | `CLAUDE_CONFIG_DIR=~/.claude-9rt claude -p --tools "Read,Grep" --model <alias> --effort low "<prompt>"` | `--tools` allowlist | `cl-9rt` is a shell alias and does not exist in a non-interactive shell — run the expanded literal; the gateway may route an alias to a non-Anthropic core |
 | **claude in-harness subagent** | Agent tool, `model` passed explicitly | the agent file's `tools:` frontmatter | an omitted `model` inherits the caller's top tier; the Agent tool has no `effort` parameter at all, so a declared effort is decorative |
@@ -61,10 +63,10 @@ Probe exactly two things, once, at the moment of assigning a lane: liveness/quot
 
 ## Cross-CLI worker (Claude Code lead → agy headless)
 
-Verified by real runs, 2026-08-01; model re-probed 2026-08-15. Invocation, flag order load-bearing:
+Verified by real runs, 2026-08-01; model re-probed 2026-09-26. Invocation, flag order load-bearing:
 
 ```
-agy --model gemini-3.7-flash-high --mode plan --output-format json -p "<prompt>"
+agy --model gemini-3.8-flash-high --mode plan --output-format json -p "<prompt>"
 ```
 
 | Fact | Design consequence |
@@ -77,7 +79,7 @@ agy --model gemini-3.7-flash-high --mode plan --output-format json -p "<prompt>"
 | **[obs]** Measured on a real read-only repo sweep: 8.2s wall / 3.4s model time, correct answer; ~20–26k tokens of fixed input overhead per call (agy's system prompt plus `~/.gemini/GEMINI.md`). *A prior version of this row cited one observed `cache_read_tokens: 32621` as evidence that repeat calls hit a warm cache. That reading was too generous — see § Stateful workers, where a controlled three-turn test shows the cache is unreliable and the latency curve is the real constraint.* | The fixed overhead means this mechanism pays for itself on a non-trivial sweep, not on a one-line lookup — the same shape as the "self-contained question" cutoff already in the Step 2 mechanism table. |
 | **[obs]** The `json`/`stream-json` output carries `usage`: `input_tokens`, `output_tokens`, `thinking_tokens`, `cache_read_tokens`, plus `conversation_id`. | Cost is measurable per call — but it is invisible to `council_cost.py`, which only parses the Claude Code session transcript. The lead must add it to the close-out tally by hand (`SKILL.md` Step 6). |
 | **[obs]** agy 1.1.9 expands skills in print mode, so `agy -p "/akiflow …"` resolves the skill; `akiflow` is already deployed to agy at `~/.gemini/config/skills/akiflow`. | A cross-CLI call can invoke the skill itself, not just an ad hoc prompt — relevant if a future revision routes part of a run through agy directly. |
-| **[owner]** + **[obs]** Model choice inside agy is not free-form. **`gemini-3.7-flash-high` is the default discovery tier** (owner directive, 2026-08-15, superseding the prior `gemini-3.6-flash-medium` default once `gemini-3.7-flash-*` shipped — see § agy headless below for the full re-probed model list): ~1M context, generous quota. Its weakness is carelessness, not capacity — it skims. The counter is prompt precision, not a bigger model: name the exact paths, the exact question, and the exact output shape, leaving it nothing to improvise. **`claude-sonnet-4-6` / `claude-opus-4-6-thinking` inside agy are quota-scarce even on a Pro plan** (owner-reported) and additionally sit on the no-cache resume curve above. | Route discovery to `gemini-3.7-flash-high` by default and hand it a fully-specified task. Reach for agy's Claude tiers only for a single-shot, self-contained, high-value call where context and cache are demonstrably under control — never for a conversation, never as a habit. When strong-model judgment is needed *and* stateful, that is a Claude session id, not agy. |
+| **[owner]** + **[obs]** Model choice inside agy is not free-form. **`gemini-3.8-flash-high` is the default discovery tier** (owner rule, 2026-08-15: the newest Flash `-high` tier is the default; re-pointed 2026-09-26 when `gemini-3.8-flash-*` shipped — see § agy headless below for the full re-probed model list): ~1M context, generous quota. Its weakness is carelessness, not capacity — it skims. The counter is prompt precision, not a bigger model: name the exact paths, the exact question, and the exact output shape, leaving it nothing to improvise. **`claude-sonnet-4-6` / `claude-opus-4-6-thinking` inside agy are quota-scarce even on a Pro plan** (owner-reported) and additionally sit on the no-cache resume curve above. | Route discovery to `gemini-3.8-flash-high` by default and hand it a fully-specified task. Reach for agy's Claude tiers only for a single-shot, self-contained, high-value call where context and cache are demonstrably under control — never for a conversation, never as a habit. When strong-model judgment is needed *and* stateful, that is a Claude session id, not agy. |
 | **[obs]** A flash-tier worker (`gemini-*-flash-*`, any generation) is for **retrieval, never for judgment**. | akiflow's thinking floor turns on the FACT/CONSTRAINT/ASSUMPTION distinction, which the skill already names as the one unrecoverable error to mislabel — exactly what a cheap model does worst. Hard rule wherever this mechanism is used, in the same voice as the existing "never downgrade implementation to save cost": retrieval only. |
 
 ## Cost model
@@ -110,7 +112,7 @@ Skills are deployed unmodified to five hosts, and **[doc]** Cursor additionally
 |---|---|---|---|---|---|
 | Claude Code | `haiku` (no `--effort`) | `sonnet` | `opus`, or `inherit` from the lead | agent frontmatter `model:`; Agent tool `model`; `claude -p --model <alias> --effort <e>` | **[obs]** verified across this file |
 | Cursor (IDE + `agent` CLI) | Composer family — the current id from Cursor's model picker (`composer-2`-style), never an API-pool Claude/GPT model | `inherit` (the session's model) | `inherit`, or the session's top API-pool model | `.cursor/agents/*.md` or `~/.claude/agents/*.md` frontmatter `model: inherit \| <id>[effort=…]`; `agent -p --model <id>` | **[doc]** field and syntax; **UNCONFIRMED** how Cursor treats a Claude alias (`haiku`) it cannot resolve — reopen trigger: one measured Cursor run of an `aki-hands` spawn |
-| Antigravity `agy` | `gemini-3.7-flash-high` (§ Cross-CLI worker) | `gemini-3.1-pro-low` | `gemini-3.1-pro-high` (`claude-opus-4-6-thinking` is quota-scarce, § agy headless) | `agy --model <slug>` — effort is inside the slug; agy 1.1.6+ agent markdown carries `model` | **[obs]** 2026-08-15 |
+| Antigravity `agy` | `gemini-3.8-flash-high` (§ Cross-CLI worker) | `gemini-3.1-pro-low` | `gemini-3.1-pro-high` (`claude-opus-4-6-thinking` is quota-scarce, § agy headless) | `agy --model <slug>` — effort is inside the slug; agy 1.1.6+ agent markdown carries `model` | **[obs]** 2026-09-26 |
 | Codex CLI | UNCONFIRMED low-cost alias | `[agents] default_subagent_model` in `config.toml`; `codex exec -c model=<id> -c model_reasoning_effort=medium` | same model, `model_reasoning_effort=xhigh` | `config.toml [agents]`, per-agent `model`; `codex exec -c …` | **[doc, secondary]** 2026-09-08, model ids drift monthly — read them from `codex` itself |
 | Kiro CLI | `qwen3-coder-next` (0.05×) or `claude-haiku-4.5` (0.4×) | `auto` (1×) or `claude-sonnet-4.5` (1.3×) | Opus-class, ~22× — rarely worth it on this host | `kiro-cli chat --no-interactive --model <id> --effort <e>`; custom agent JSON `model` | **[obs]** 2026-08-02 list; multipliers re-read with `--list-models` |
 | Grok CLI | UNCONFIRMED | `grok-build-0.1` default | UNCONFIRMED | `grok -p` (`--model` flag unconfirmed) | **[doc, secondary]** 2026-09-08 |
@@ -150,7 +152,7 @@ Full narrative and the measurements behind these rows: `docs/research/headless-c
 
 ### agy headless — see § Cross-CLI worker above
 
-**[obs]** Re-probed 2026-08-15 (prior check 2026-08-02 predates the `gemini-3.7-flash-*` release — do not cite the old list), `agy models`: `gemini-3.7-flash-{low,medium,high}`, `gemini-3.6-flash-{low,medium,high}`, `gemini-3.5-flash-{low,medium,high}`, `gemini-3.1-pro-{low,high}`, **`claude-sonnet-4-6`**, **`claude-opus-4-6-thinking`**, `gpt-oss-120b-medium`. Also present: `--json-schema`, `--effort`, `--agent`, `--add-dir`, `--print-timeout`, `--disable-slash-commands`, and an `agents` subcommand (empty on this machine — no custom agy agents defined).
+**[obs]** Re-probed 2026-09-26 (agy 1.2.11; the 2026-08-15 list predates the `gemini-3.8-flash-*` release — do not cite it), `agy models`: `gemini-3.8-flash-{low,medium,high}`, `gemini-3.7-flash-{low,medium,high}`, `gemini-3.6-flash-{low,medium,high}`, `gemini-3.1-pro-{low,high}`, **`claude-sonnet-4-6`**, **`claude-opus-4-6-thinking`**, `gpt-oss-120b-medium`. Also present: `--json-schema`, `--effort`, `--agent`, `--add-dir`, `--print-timeout`, `--disable-slash-commands`, and an `agents` subcommand (empty on this machine — no custom agy agents defined).
 
 *Consequence:* a Claude-family model can be reached **on the Antigravity quota**. The vendor paying and the model reasoning are independent choices, which is a second axis the Step 2 mechanism table did not previously have.
 

package/skills/akihelp/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: akihelp
-description: Introduce the whole Aki Claude Code system — installed skills, the akirule passive rule router (3 tiers), the deep-think passive/active split, and a painpoint-to-prompt table for the situations people actually hit — by reading live installed state, never a hardcoded inventory. Use when the user asks what Aki tools/rules/skills are available, how the system works, or what to say for a recurring problem they keep running into.
+description: Introduce the whole Aki Claude Code system — installed skills, the akirule rule router (imported, routes by meaning), the deep-think passive/active split, and a painpoint-to-prompt table for the situations people actually hit — by reading live installed state, never a hardcoded inventory. Use when the user asks what Aki tools/rules/skills are available, how the system works, or what to say for a recurring problem they keep running into.
 ---
 
 # akihelp — live introduction to the Aki system
 
-Invoke with `/akihelp`, or when the user asks what's available in this setup ("what can this do", "hệ thống Aki có gì", "how do I use this", "what skills do I have"). Goal: give the user a clear, accurate picture of the whole Aki Claude Code system so they can fully exploit it.
+Invoke with `/akihelp`, or whenever the user asks, in any wording, what this setup offers or how to use it. Goal: give the user a clear, accurate picture of the whole Aki Claude Code system so they can fully exploit it.
 
 **This skill must never go stale.** Do not hardcode a skill/rule inventory in this file — read live state every time it runs, so the output is always correct even after `install.sh` adds, renames, or removes something.
 
@@ -18,8 +18,8 @@ Invoke with `/akihelp`, or when the user asks what's available in this setup ("w
 
    - **Skills (active, user-invoked)** — one row per aki-skill: its `/name`, its one-line description (from frontmatter), and when to reach for it.
    - **Agent definitions (who the work gets handed to)** — one row per installed `aki-` agent from step 3: what it is for, and the property that is mechanical rather than promised (its `tools:` list, which is what makes a read-only agent actually read-only, and its `model:`, so a tier is never improvised). Say the thing people get wrong: this is a catalog, not a roster — an agent is spawned because a specific requirement needs it, never because it exists.
-   - **Passive system (akirule)** — explain the 3 tiers: Core rules always loaded every turn; Contextual/Analytical rules auto-loaded on signal match; full load via an explicit phrase ("nạp full", "load all rules"). Note that `akirule` itself is hidden from the `/` menu by design (`user-invocable: false`) — it runs passively, not as a command.
-   - **One brain, three modes** — `METHOD-deep-think.md` is read passively by akirule inside normal tasks (brief, inline, at most one clarifying question), as a triggered self-run when an `agent.A3` deep-think trigger holds (non-interactive, depth scaled to difficulty, ends in decide-and-report or escalation), and actively by `/akithink` (full 5-phase interactive session for big/hard-to-reverse/goal-ambiguous decisions). Short version of the comparison, not the full METHOD text.
+   - **Passive system (akirule)** — explain the load mechanisms: core rules and the router always loaded (`@`-imported by `CLAUDE.md`); contextual/analytical rules read when the task's domain matches a route — by meaning, never keywords; full load when the owner asks for the whole corpus. `akirule` is hidden from the `/` menu by design (`user-invocable: false`) — it is imported, not a command.
+   - **One brain, three modes** — `METHOD-deep-think.md` is read passively by the router inside normal tasks (brief, inline, at most one clarifying question), as a triggered self-run when an `agent.A3` trigger holds or `/akithink` self-runs on a genuine decision (non-interactive, depth scaled to difficulty, ends in decide-and-report or escalation), and interactively by `/akithink` when the owner asks for a session. Short version of the comparison, not the full METHOD text.
    - **Editing rules** — this whole system is generated from a source repo (akidevrule); the installed copies under `~/.aki/akidevrule` and `~/.claude` are deployed output, never edited directly. Changes go through the source repo + `install.sh`. Note for context: the same skill corpus (not the rule corpus) is also synced by `install.sh` to Antigravity/Gemini and to Codex, Kiro, and Grok CLIs on this machine if present — this skill itself only introduces the Claude Code side.
 
 5. Render a **painpoint → what to say** table. This is the section most people actually need: a capability list tells them what exists, this tells them which words to type when a specific problem is in front of them. Build every row from what steps 1–3 actually returned, and **drop any row whose skill or rule file did not appear there** — a row pointing at something uninstalled is worse than a missing row.
@@ -29,7 +29,7 @@ Invoke with `/akihelp`, or when the user asks what's available in this setup ("w
    | Styles are sprawling — duplicated classes, hardcoded colors, CSS piling up in component `<style>` blocks | *"Audit CSS this repo per `ui.C`. Read-only, produce a plan."* then a separate *"Clean per the plan, one pattern per pass."* | `RULE-ui-pattern.md` §C — the inversion check runs first and decides whether the rest is even worth doing |
    | Docs describe something the code no longer does | *"Drift audit the docs against the code."* | `RULE-docs.md` §C — severity split across wrong / stale / incomplete / cosmetic |
    | Long half-finished working tree, unclear what is safe to commit | `/akigitcommit` | Triages finished vs mid-edit vs abandoned vs accidental **before** grouping; stages by explicit path, never `git add -A` |
-   | Work is finished but not pushed, and they want to know if it is genuinely shippable | *"Is this ready to ship?"* / *"xong chưa"* | `RULE-release.md` B7 pre-ship gate — a pass/fail check, not a document |
+   | Work is finished but not pushed, and they want to know if it is genuinely shippable | *"Is this ready to ship?"* | `RULE-release.md` B7 pre-ship gate — a pass/fail check, not a document |
    | A decision is big, hard to reverse, or the real goal is still fuzzy | `/akithink` | Full 5-phase session: restate → goal excavation → first principles → mandatory critique → decision record. Small reversible calls should just be decided instead |
    | Replies are padded, or lines are hard-wrapped mid-sentence | Name the penalty card: *"`[FLUFF]`"* / *"`[WRAP]`"* / *"`[YAP]`"*, or run `/akilint` | `RULE-agent-behavior.md` §0. `/akilint` runs the deterministic detector for the two mechanical cards; `[FLUFF]` stays human judgment and no script claims it |
    | One task genuinely needs several kinds of judgment at once (architecture *and* UX *and* market) | `/akiflow` | Lead-coordinated council with `aki-challenger`'s subtraction pass ("what can be cut?") and a mechanical closure gate. Overkill for ordinary work — say so plainly rather than routing everything here |
@@ -40,8 +40,8 @@ Invoke with `/akihelp`, or when the user asks what's available in this setup ("w
    | The interface works but feels confusing or people do not complete the flow | *"Review the UX of this screen."* | `METHOD-ux-psych.md` — a behavioral lens, distinct from `RULE-ui-pattern.md` which owns visual structure |
    | A pricing, positioning, or audience call | *"Who is this for and what should it cost?"* | `RULE-biz.md` — plus `docs/biz/` as the project's source of truth |
    | An analysis in chat is too dense to read as text | `/akihtmlreport` | Renders the analysis already in the conversation as one self-contained HTML file — it visualizes, it does not re-analyze |
-   | Unsure whether a rule loaded at all | *"nạp full"*, or just read the `[RULES]` line | Every response carries a `[RULES]` receipt naming the whole rule context and a `missing:` field, so "the rule never arrived" is visibly different from "the rule arrived and was ignored" — the two have opposite fixes. `nạp full` is the Tier 2 escape hatch that reads everything |
+   | Unsure whether a rule loaded at all | Read the `[RULES]` line, or ask to load the whole corpus | Every response carries a `[RULES]` receipt naming every rule file in context, so "the rule never arrived" (absent from the line) is visibly different from "the rule arrived and was ignored" — the two have opposite fixes. A full-load request reads everything |
 
-6. Close with the one caveat that changes how people use all of the above: **`akirule` is a skill, so it is best-effort** — it applies only when the model chooses to invoke it and a signal matches. Only `index.md`, `RULE-agent-behavior.md`, `RULE-coding.md` and `RULE-pattern-core.md` are guaranteed, because the harness `@`-imports them through `CLAUDE.md`. When something must be deterministic, name the file in the prompt (*"Read `~/.aki/akidevrule/RULE-ui-pattern.md`, then …"*) instead of trusting the signal to fire.
+6. Close with the one caveat that changes how people use all of the above: **the router is guaranteed, a routed file is not** — `index.md`, the three core rule files and the router are `@`-imported through `CLAUDE.md`, but a contextual file enters context only when the model `Read`s it on a route match. When something must be deterministic, name the file in the prompt (*"Read `~/.aki/akidevrule/RULE-ui-pattern.md`, then …"*) instead of trusting the signal to fire.
 
 7. Keep the output scannable: compact tables or short bulleted sections, not an essay. Respond in the user's language, and translate the example prompts into that language rather than pasting them verbatim in English.

package/skills/akihtmlreport/SKILL.md

@@ -5,7 +5,7 @@ description: Visualize a complex report that already exists in the conversation
 
 # akihtmlreport — single-file visual report extraction
 
-Invoke with `/akihtmlreport`, or when the user asks in their own words to extract the discussion into a visual file ("trích xuất ra html", "xuất báo cáo trực quan", "làm file report", "export this to html"). Its purpose is single and narrow: turn a complex analysis or report that already exists in this conversation into one self-contained HTML file for dense, at-a-glance reading — **nothing else, no new analysis**. Not a replacement for chat responses, and not something to reach for by default.
+Invoke with `/akihtmlreport`, or when the user asks, in any wording, to turn the discussion into a visual file. Its purpose is single and narrow: turn a complex analysis or report that already exists in this conversation into one self-contained HTML file for dense, at-a-glance reading — **nothing else, no new analysis**. Not a replacement for chat responses, and not something to reach for by default.
 
 ## When this skill actually applies
 

package/skills/akilint/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: akilint
-description: Mechanical format lint for the penalty-card classes of RULE-agent-behavior.md §0 — hard-wrapped code comments and markdown prose ([WRAP]) and oversize comments ([YAP]) — via the shared scythe.py detector. Deterministic file:line output; judgment stays with the session. Use when the user asks to lint/quét formatting, mentions wrapline, "bẻ dòng", "comment lảm nhảm", or calls a penalty card ([WRAP]/[YAP]/[FLUFF]) on recent output.
+description: Mechanical format lint for the penalty-card classes of RULE-agent-behavior.md §0 — hard-wrapped code comments and markdown prose ([WRAP]) and oversize comments ([YAP]) — via the shared scythe.py detector. Deterministic file:line output; judgment stays with the session. Use whenever formatting is in question — the user wants lines or comments checked, complains that text is hard-wrapped or comments are bloated, or calls a penalty card ([WRAP]/[YAP]/[FLUFF]) on recent output.
 user-invocable: true
 ---
 

package/skills/akirule/SKILL.md

@@ -1,157 +1,71 @@
 ---
 name: akirule
-description: Aki's contextual rule router — invoke BEFORE acting whenever the task touches any of - .md/.vue/.css/.tsx/.rs/.sql files; docs, plan, README, CHANGELOG; UI, component, CSS, tailwind; SEO, schema, sitemap; release, version, commit, push, deploy; DB schema, migration; Tauri; i18n, UI copy; pricing, biz; UX review; refactor, flow tracing; audit or minimize sweeps; big decisions (should we / có nên). Full corpus load on "nạp full". Core rules are not routed here — the harness embeds them via CLAUDE.md.
+description: Aki's contextual rule router — route EVERY task turn before acting, by what the task means (the domain it touches and the kind of act — write, decide, audit, ship), with listed signals as evidence, never as the test. Domains: docs and any .md, UI copy and i18n, frontend components and CSS, SEO, commit/push/deploy/release/CI, database schema and migrations, Nuxt/Cloudflare, Tauri/Rust, pricing and positioning, UX, guards and risk sizing, flow bugs, audits and minimization, conformance to a reference, and any decision or critique. Loads each contextual RULE/METHOD file whose domain the task touches; full corpus on an explicit load-everything request. Core rules are not routed here — the harness embeds them via CLAUDE.md.
 user-invocable: false
 ---
 
-## What this skill does and does not guarantee
+# akirule — contextual rule router
 
-**Nothing in this file is guaranteed to run.** A skill loads only when the model chooses to invoke it, so every rule routed below is best-effort.
+## Delivery
 
-The rules that must apply unconditionally are not here. `index.md`, `RULE-agent-behavior.md`, `RULE-coding.md` and `RULE-pattern-core.md` are embedded by the harness through `@` imports in `~/.claude/CLAUDE.md`, which is read mechanically at session start. Do not move them back into this file: an `@` path inside a skill body is not expanded by the harness the way it is inside `CLAUDE.md`, so declaring them here would look like an import while loading nothing.
+- **Claude Code:** this file is `@`-imported by `~/.claude/CLAUDE.md`, so it is in context every session without a model decision. Do not invoke the skill as well — the routing below is already loaded.
+- **Antigravity (IDE and `agy`):** routing is native — every rule is installed as `akirule-<topic>.md` (`agent` `always_on`, the rest by descriptions the installer generates from the routes below), so do not invoke this skill there.
+- **Other harnesses (Codex, Kiro, Grok):** it is a skill; invoke it before acting on any task turn.
+- **Not routed here:** `index.md`, `RULE-agent-behavior.md`, `RULE-coding.md`, `RULE-pattern-core.md` — core, harness-embedded, never `Read` again and never listed as `(router)`.
+- What stays best-effort is the second hop: reading a routed file is still the model's `Read`. Nothing below is optional because of that — it is the reason the receipt exists.
 
-The last two used to be routed here as "default ON" Tier 1 entries. That phrasing promised a guarantee the mechanism could not deliver — a file routed by a skill loads only if the model first decides to invoke the skill — and the observed failure was not the rules being read and ignored but never being read at all. Do not re-add them below: they are already in context on every turn, so a signal block for them would only produce a redundant `Read`.
+## How to route — meaning first, signals as evidence
 
-## Addressing scheme (recall only — does not affect routing)
+1. **Every task turn, before acting**, name the task in two terms: the **domains** it touches (the artifact and its subject) and the **act** (create/change, evaluate/decide, audit/verify, ship). Route on that classification in whatever language or phrasing it arrived. A signal is evidence of a domain, never the test: a request that names no listed signal still routes, a synonym or paraphrase of one counts as the signal itself, and a word used in passing does not.
+2. **Load every file whose domain the task touches** — several at once is normal. **When in doubt, load:** a false positive costs a few tokens, a false negative ships wrong work.
+3. **The artifact type alone is sufficient evidence** — the route applies whether or not the project has the matching folder or maturity.
+4. **Skip a file already loaded this conversation.**
+5. **A project binding is a standing signal:** when the project's own `CLAUDE.md`/docs bind a stack, a reference implementation, or a domain, its route is ON for every task in that project without waiting for the message to mention it.
 
-Every rule file is internally organized into groups `A`/`B`/`C` and numbered items `1`/`2`/`3…` (e.g. `coding.B2`, `stack.C1`). `topic` = the manifest's Topic column in `index.md` — usually the filename minus its `RULE-`/`METHOD-` prefix; the audit methods keep their short topics (`flow`, `zero-trust`, `subtract`). This is a naming convention for referring to a specific rule precisely — it has no effect on which files load or when; that is still governed entirely by the tiers below. Full map: `~/.aki/akidevrule/index.md`.
+## Routes
 
----
+All files live in `~/.aki/akidevrule/`.
 
-## Tier 1 — Contextual loading
-
-**Sensitivity bias: when in doubt, load. A false positive (loading an unused file) costs a few tokens. A false negative (missing a rule) causes wrong behavior.**
-
-Before responding, scan the user message and any file paths mentioned. For each rule below: if ANY single signal matches → Read that file immediately, before generating a response.
-
-Skip the Read if that file was already loaded earlier in this conversation — a signal match on an already-loaded rule costs a redundant Read and changes nothing.
-
-**A file extension alone is a sufficient signal.** Touching a `.md` loads `RULE-docs.md`; a `.vue`/`.css` loads `RULE-ui-pattern.md`; `.rs`/`Cargo.toml` loads `RULE-stack-tauri.md`; `.sql`/`migrations/` loads `RULE-db-design.md`. The project does **not** need a matching folder structure, a `docs/` tree, or an existing design system first — match on what is being touched, not on how mature the project is. The keyword and action lists below are additional entry points, never a required second condition.
-
-### RULE-coding.md · RULE-pattern-core.md — not routed, already loaded
-Both are core `@` imports (see the section above) and are in context on every turn without this skill running. Nothing to match, nothing to `Read`, and they never appear in a load-confirmation line.
-
-### RULE-docs.md
-Load if message or file path contains any of:
-- **Keywords:** `docs`, `CLAUDE.md`, `README`, `PLAN`, `plan/`, `diagram`, `mermaid`, `architecture`, `arch/`, `doc sync`, `documentation`, `docs/feat/`, `plan lifecycle`, `tài liệu`, `sơ đồ`, `kiến trúc`
-- **Keywords (drift audit):** `drift`, `audit docs`, `stale docs`, `outdated docs`, `out of date`, `docs khớp code`, `còn khớp`, `lệch`, `lỗi thời`, `rà soát tài liệu`, `docs cũ`, `kiểm tra tài liệu`
-- **Paths:** **any `.md` file, anywhere** — writing or editing Markdown *is* a docs task; do not wait for a `docs/` folder to exist. Also `docs/**`, `PLAN.md`, `CLAUDE.md`, `README.md`, `CHANGELOG.md`, `*.mdx`, `SKILL.md`
-- **Actions:** creating, editing, moving, or completing any plan or doc file; checking whether docs still match the code after the fact (`docs.C`)
-
-### RULE-content-write.md
-Load if message or file path contains any of:
-- **Keywords:** `button`, `label`, `heading`, `error message`, `tooltip`, `empty state`, `i18n`, `locale`, `translation`, `t(`, `$t(`, `meta title`, `meta description`, `og:`, `JSON-LD`, `FAQ`, `landing page`, `UI text`, `nội dung UI`, `nội dung giao diện`, `nhãn`, `thông báo lỗi`, `semantic stability`
-- **Paths:** `locales/**`, `i18n/**`, `*.i18n.*`, `public/content/**`; any file where a string a user will read is being added or renamed
-- **Actions:** renaming a concept or term used across the product
-
-### RULE-stack-akiNuxtCf.md
-**Default ON when the project CLAUDE.md references the Aki web stack (Nuxt/Cloudflare — AkiNuxtCf).** Skip only when the task is provably stack-independent (plain markdown, isolated script, config unrelated to the Aki frontend stack). Load if message or file path contains any of:
-- **Keywords:** `nuxt`, `vue`, `cloudflare`, `cloudflare workers`, `cf workers`, `wrangler`, `tailwind`, `composable`, `middleware`, `nuxt layout`, `nuxt plugin`, `component`, `useRoute`, `useFetch`, `definePageMeta`, `nitro`, `vite`, `breadcrumb`, `scroll-to-top`, `back-to-home`, `layout chrome`, `useBreadcrumb`
-- **Paths:** `components/**`, `pages/**`, `composables/**`, `layouts/**`, `plugins/**`, `middleware/**`, `wrangler.toml`, `nuxt.config.*`, `tailwind.config.*`, `app.vue`
-
-### RULE-ui-pattern.md
-Load if message or file path contains any of:
-- **Keywords (enforcement):** `component`, `vue`, `nuxt`, `tailwind`, `css`, `class`, `style`, `design token`, `token`, `variant`, `design system`, `atomic design`, `pattern class`, `@apply`, `@layer`, `BaseButton`, `c-btn`, `c-card`
-- **Keywords (audit):** `dọn dẹp`, `class trùng`, `duplicate class`, `duplicate CSS`, `trùng lặp`, `audit CSS`, `refactor CSS`, `refactor UI`, `arbitrary value`, `quét class`, `w-[`, `text-[`
-- **Keywords (minimization):** `tối giản`, `giảm CSS`, `bớt CSS`, `minimize CSS`, `reduce CSS`, `gọn lại`, `CSS rác`, `style block`, `inline style`, `scoped style`, `@theme`, `theme block`, `token drift`, `nhiều CSS quá`, `code CSS nhiều`
-- **Paths:** any `.vue`, `.css`, `.scss`, or `.tsx`; `components/**`, `assets/css/**`, `tailwind.config.*`
-- **Actions:** writing/refactoring any component or style; auditing a frontend codebase for DRY/SOLID violations
-
-### RULE-seo.md
-Load if message or file path contains any of:
-- **Keywords:** `seo`, `schema`, `sitemap`, `robots`, `canonical`, `usePageSeo`, `useSchemaOrg`, `JSON-LD`, `structured data`, `og:`, `ogImage`, `hreflang`, `alternateName`, `sameAs`, `knowsAbout`, `LLM visibility`, `AI visibility`, `AI Overview`, `entity`, `schema.org`, `DefinedTerm`, `validate-seo`, `meta title`, `meta description`, `OG image`, `trailing slash`
-- **Paths:** `docs/seo/**`, `docs/ref/seo*`, `scripts/validate-seo*`, `composables/usePageSeo*`, `composables/useSeoSchemas*`
-- **Actions:** creating a new page, adding schema, configuring sitemap or robots
-
-### RULE-release.md
-Load if message or file path contains any of:
-- **Keywords:** `release`, `release note`, `release notes`, `changelog`, `CHANGELOG`, `version`, `versioning`, `semver`, `bump`, `bump version`, `major.minor.patch`, `releases.json`, `phát hành`, `phiên bản`, `cập nhật phiên bản`, `nâng version`
-- **Paths:** `CHANGELOG.md`, `app/data/releases.json`, `pages/releases/**`
-- **Keywords (pre-ship gate):** `chưa push`, `trước khi push`, `trước khi deploy`, `sắp release`, `chuẩn bị ship`, `pre-release`, `ready to ship`, `xong chưa`, `đã xong hết chưa`
-- **Keywords (release-ritual context — these load this rule file, they never start a run; activation is owned entirely by akiship's own gate, an imperative release order):** `akiship`, `full release`, `release trọn gói`, `chạy full release`, `ship đợt này`, `ship trọn gói`
-- **Keywords (commit/push/deploy — load even without an explicit "release" word):** `commit`, `git commit`, `push`, `git push`, `deploy`, `deployment`, `git tag`, `ship it`, `commit và push`, `push lên`, `đẩy lên`, `triển khai`
-- **Keywords (registry publish — `release.B9`):** `npm publish`, `publish`, `npm`, `npx`, `registry`, `crates.io`, `cargo publish`, `PyPI`, `twine`, `2FA`, `OTP`, `lên npm`
-- **Keywords (migration & post-deploy — `release.B5`, `release.B11`):** `migration`, `migrate`, `schema change`, `ALTER TABLE`, `add column`, `db migration`, `health endpoint`, `/health`, `post-deploy`, `smoke test`, `chạy migration`, `đổi schema`
-- **Keywords (post-push CI — `release.B10`):** `CI`, `GitHub Actions`, `workflow run`, `gh run`, `CI fail`, `CI đỏ`, `build fail`, `test fail`
-- **Actions:** committing or pushing code, deploying, shipping a change that should be recorded for users or maintainers; bumping a version; checking whether finished-but-unpushed work is actually shippable (`release.B7`); running the full release ritual unattended (`release.B8`, `/akiship`); verifying CI after a push (`release.B10`)
-
-### RULE-stack-tauri.md
-**Default ON for any Tauri project context.** Skip only when the task is provably unrelated to the Tauri/Rust backend (pure frontend copy change with no `src-tauri` involvement, isolated doc edit). Load if message or file path contains any of:
-- **Keywords:** `tauri`, `#[tauri::command]`, `invoke(`, `spawn_blocking`, `async_runtime`, `Cargo.toml`, `tauri.conf.json`, `capabilities`, `IPC`, `blocking UI`, `freeze`, `treo app`, `đứng app`, `block UI`
-- **Paths:** any `.rs`; `src-tauri/**`, `tauri.conf.json`, `Cargo.toml`, `capabilities/*.json`
-- **Actions:** adding/editing any `#[tauri::command]`, touching window/IPC code, bumping app version, diagnosing an app freeze/hang
-
-### RULE-db-design.md
-Load if message or file path contains any of:
-- **Keywords:** `schema`, `migration`, `D1`, `SQL`, `database design`, `ERD`, `refactor DB`, `event sourcing`, `bounded context`, `normalization`, `1NF`, `table design`, `thiết kế db`, `thiết kế database`, `migration DB`
-- **Paths:** any `.sql`; `migrations/**`, `schema.sql`, `**/d1/**`
-- **Actions:** designing a new table/schema, writing a DB migration, refactoring how data is stored
-
-### METHOD-audit-flow.md
-Load if message contains any of:
-- **Keywords:** `refactor`, `restructure`, `simplify`, `fragile`, `complicated`, `state machine`, `async chain`, `tại sao phức tạp`, `luồng`, `luồng xử lý`, `tracing`, `cause and effect`, `over-guarded`, `nested conditional`, `điều kiện lồng nhau`, `timing issue`, `race condition`, `tái cấu trúc`, `đơn giản hóa`
-- **Context:** fixing a bug spanning multiple files, tracing cause and effect across a chain
-
-### RULE-biz.md
-Load if message or file path contains any of:
-- **Keywords:** `pricing`, `price`, `monetization`, `monetize`, `positioning`, `USP`, `target audience`, `customer`, `market`, `marketing`, `conversion`, `landing page`, `business model`, `revenue`, `tier`, `plan`, `subscription`, `giá`, `định giá`, `kiếm tiền`, `khách hàng`, `thị trường`, `đối tượng`, `chuyển đổi`, `mô hình kinh doanh`, `doanh thu`, `gói`, `định vị`
-- **Paths:** `docs/biz/**`
-- **Context:** any market-facing decision — evaluating an idea's commercial shape, writing/reviewing landing or sales copy, creating or editing `docs/biz/`, deciding what to charge or who the product is for
-
-### METHOD-ux-psych.md
-Load if message contains any of:
-- **Keywords:** `UX`, `user experience`, `usability`, `user behavior`, `user psychology`, `onboarding`, `user flow`, `friction`, `cognitive load`, `empty state`, `first run`, `dead end`, `dark pattern`, `trải nghiệm người dùng`, `tâm lý người dùng`, `hành vi người dùng`, `khó dùng`, `rối`, `luồng người dùng`, `đánh giá giao diện`, `review UI`, `review UX`
-- **Context:** evaluating an interface or flow through user behavior (not just visual styling — that is `RULE-ui-pattern.md`), designing an onboarding/conversion flow, diagnosing "why don't users do X"
-
-### METHOD-audit-zero-trust.md
-Load if message contains any of:
-- **Keywords:** `audit khắt khe`, `ép rule`, `force audit`, `quét tuyệt đối`, `zero-trust audit`, `rà soát toàn bộ`, `quét toàn dự án`, `chứng minh sạch`, `audit tuyệt đối`
-- **Context:** when the user asks for an uncompromising sweep — of the whole project or of a change plus everything that reads it — that must be driven by detectors rather than by impression. Read-only: it produces a short findings report, not fixes.
-
-### METHOD-deep-think.md
-Load if message contains any of:
-- **Keywords:** `new feature`, `tính năng mới`, `should we`, `có nên`, `simplest way`, `đơn giản nhất`, `is this worth`, `có đáng`, `tradeoff`, `scope creep`, `mở rộng scope`, `premature`, `complexity`, `abstraction`, `tooling`, `first principles`, `tư duy nguyên bản`, `phản biện`, `mục tiêu tối thượng`, `one-way door`, `quyết định lớn`, `decision record`, `pre-mortem`, `evaluate`, `assess`, `review the approach`, `worth refactoring`, `good idea`, `side effect`, `edge case`, `đánh giá`, `bàn luận`, `nên refactor`, `đánh giá ý tưởng`, `đánh giá chiến lược`, `tác dụng phụ`, `trường hợp biên`, `leo thang`, `hỏi owner`, `mâu thuẫn`, `bế tắc`, `thử lại vẫn lỗi`, `tự chốt`
-- **Context:** architectural or tooling decision, scope or effort/value discussion, a big or hard-to-reverse decision, a request for first-principles/critique-style thinking, *discussing/evaluating* (rather than just executing) a refactor, a code review, a strategy/plan, or an idea — the four cases that trigger Module 5 (MVP focus, side-effects/edge-cases weighed by severity) — plus, at extra sensitivity: about to ask or escalate to the owner, a fix that failed twice, conflicting rules/instructions, owner wording with multiple readings. `agent.A3` is the mechanical floor for escalation; this line is additional routing sensitivity on top of it, not a replacement.
-
-### METHOD-proportionality.md
-Load if message contains any of:
-- **Keywords:** `rate limit`, `quota`, `throttle`, `abuse`, `spam`, `bot`, `exploit`, `bypass`, `tamper`, `client-side check`, `guard`, `defensive`, `hardening`, `threat model`, `attack surface`, `over-engineering`, `overthinking`, `paranoid`, `is it worth defending`, `lạm dụng`, `giới hạn`, `chặn`, `hạn mức`, `phòng thủ`, `bảo mật quá mức`, `nghĩ quá nhiều`, `vẽ vời`, `có cần chặn không`, `bao nhiêu user`, `mấy ai làm được`, `rủi ro`, `mức độ nghiêm trọng`
-- **Context:** any proposal to add, keep, size, or remove a guard / limit / validation / permission check; deciding whether a client-side restriction is enough; accepting a risk deliberately; weighing MVP speed against security or abuse resistance. Also load when a discussion is stacking protection with no evidence of who could actually reach the state being protected.
-
-### METHOD-audit-subtraction.md
-Load if message contains any of:
-- **Keywords:** `subtraction audit`, `dead code`, `unused`, `unreferenced`, `bloat`, `strip down`, `minimize the repo`, `tối giản tuyệt đối`, `tối giản tối đa`, `tinh gọn toàn bộ`, `cắt giảm tối đa`, `dọn sạch repo`, `xoá code thừa`, `code chết`, `refactor hạng nặng`, `không còn gì để bớt`, `gọn nhất có thể`
-- **Context:** a request to minimize or strip an existing repository rather than to check its correctness. Pairs with `METHOD-audit-zero-trust.md`, whose scope-lock, detector-first order and evidence classes it inherits. Read-only: it reports and plans removals, it never deletes.
+| File | Load when the task … | Signals — each stands for a concept; any synonym, in any language, counts the same (EN · VI) |
+|---|---|---|
+| `RULE-docs.md` | creates, edits, moves or completes any Markdown, doc, plan, instruction file (`CLAUDE.md`, `SKILL.md`, `README`, `CHANGELOG`), or checks docs against the code | any `.md`, `docs/**`, `SKILL.md`; docs, plan, README, diagram, mermaid, architecture, drift, stale/outdated docs · tài liệu, sơ đồ, kiến trúc, lệch, lỗi thời, rà soát tài liệu |
+| `RULE-content-write.md` | writes, renames or audits text an end user reads — UI copy, messages, labels, i18n strings, page metadata copy | button/label/heading, error message, tooltip, empty state, tone, i18n, locale, translation, `locales/**`, renaming a user-facing term · nội dung giao diện, nhãn, thông báo lỗi, bản dịch |
+| `RULE-stack-akiNuxtCf.md` | works in a Nuxt / Vue / Cloudflare Pages-Workers project — ON for the whole project when its binding names that stack | `.vue`, `nuxt.config`, `wrangler.toml`, Nuxt, Vue, Cloudflare Workers/Pages, D1, KV, Nitro, composable, middleware, `useFetch`, breadcrumb, layout width |
+| `RULE-stack-tauri.md` | works in a Tauri / Rust desktop project — ON for the whole project | `.rs`, `src-tauri/`, `tauri.conf.json`, `Cargo.toml`, `#[tauri::command]`, IPC, `spawn_blocking`, freeze, hang, blocking UI, settings breaking after an upgrade · treo app, đứng app, đơ, khựng |
+| `RULE-ui-pattern.md` | builds, styles, minimizes or audits frontend components, classes, tokens or style blocks | `.vue`/`.css`/`.scss`/`.tsx`, Tailwind, class, style block, inline style, design token, variant, `@apply`, `@theme`, arbitrary value, duplicate/bloated CSS, looks inconsistent · dọn CSS, class trùng, tối giản CSS, nhiều CSS quá |
+| `RULE-seo.md` | shapes how pages are found or represented — metadata, structured data, sitemap/robots, canonical/hreflang, search or AI visibility, entity identity | SEO, meta title/description, OG image, JSON-LD, schema.org, sitemap, robots, canonical, hreflang, trailing slash, AI visibility, not indexed · không lên Google |
+| `RULE-release.md` | records, versions, commits, pushes, tags, publishes, deploys or migrates; watches CI or verifies a deploy; or asks whether finished work is shippable | commit, push, deploy, tag, release, release notes, `CHANGELOG`, version, semver, bump, publish, npm/registry, 2FA/OTP, CI, GitHub Actions, migration, post-deploy, health check, "is it done / ready to ship?" · phát hành, phiên bản, nâng version, đẩy lên, triển khai, xong chưa, CI đỏ |
+| `RULE-db-design.md` | designs or changes the shape of stored data — schema, migration, query structure, data refactor | `.sql`, `migrations/`, schema, table, column, index, D1, SQL, ERD, event sourcing, normalization, keeping history of a value, choosing a database · thiết kế DB, đổi schema, thêm cột |
+| `RULE-biz.md` | makes a market-facing decision — audience, positioning, pricing, offer, sales/landing copy, `docs/biz/` | pricing, plan/tier, subscription, monetization, revenue, positioning, USP, target audience, customer, market, conversion, landing page, `docs/biz/` · định giá, gói, khách hàng, thị trường, định vị, doanh thu |
+| `METHOD-audit-flow.md` | refactors or debugs across a chain of steps or files, or meets guards/fallbacks accumulating around one path, async/state/timing trouble | refactor, restructure, simplify, fragile, flaky, race condition, timing, state machine, async chain, nested conditionals, repeated guards, patchwork, a guard or fallback for a state the docs rule out, a fix that keeps not holding · luồng xử lý, điều kiện lồng nhau, tái cấu trúc, chắp vá, hiển nhiên, native flow, lúc được lúc không |
+| `METHOD-deep-think.md` | evaluates, decides, critiques or discusses rather than only executes — approach choice, tradeoff, scope, value, strategy, a review of an idea/plan/rule | should we, is it worth it, which option, tradeoff, scope, first principles, critique, pre-mortem, edge case, side effect, one-way door, stuck after repeated failures, the owner hands over the decision, conflicting instructions, ambiguous wording · có nên, có đáng, đánh giá, phản biện, bế tắc, thử lại vẫn lỗi, tự chốt, mâu thuẫn |
+| `METHOD-ux-psych.md` | judges an interface or flow by how users will behave | UX, usability, onboarding, user flow, friction, cognitive load, drop-off, conversion, no feedback after an action, dead end, dark pattern · khó dùng, rối, trải nghiệm người dùng, bỏ ngang |
+| `METHOD-proportionality.md` | adds, keeps, sizes or removes a guard, limit, validation or permission, or accepts a risk deliberately | rate limit, quota, throttle, abuse, spam, bot, bypass, tamper, client-side check, hardening, threat model, over-engineering, overkill · chặn, giới hạn, lạm dụng, phòng thủ, vẽ vời, rủi ro, mấy ai làm được |
+| `METHOD-audit-zero-trust.md` | demands an uncompromising, proof-driven sweep of a project or of a change plus everything that reads it | zero-trust audit, strict audit, sweep the whole project, miss nothing, prove it with tool output · audit khắt khe, rà soát toàn bộ, quét tuyệt đối, chứng minh sạch |
+| `METHOD-audit-subtraction.md` | asks to minimize, strip or clean out what no longer needs to exist | dead code, unused, unreferenced, bloat, redundant guard or fallback, comment restating a known fact, strip down, lean as possible, heavy cleanup · code chết, code thừa, hiển nhiên, tối giản tối đa, dọn sạch repo, tinh gọn |
+| `METHOD-audit-frozen-reference.md` | judges conformance to a concrete reference implementation (another repo, a pinned version, a specific file) at any strictness | frozen/pinned reference, canonical implementation, reference project, template repo, byte-identical, structurally identical, drifted from the original · đối chiếu, giống hệt, y hệt, lệch chuẩn, khớp chuẩn, so với dự án gốc |
 
----
+**Sequential full audit** — the task asks to check a codebase thoroughly across every standard, one after another: load `zero-trust`, `flow`, `subtract`, `docs`, `content`, plus `ui` for a frontend, and run the passes in this order, each read-only: detectors (`zero-trust.B`) → structure (`pattern` laws, `flow`) → subtraction (`subtract`) → docs drift both directions (`docs.C`) → content (`content.C2`). One report, severity-ranked; fixes are a separate run (`agent.B5`).
 
-## Tier 2 — Full load
+**Deep-think depth** — when the `deep-think` route fires and the decision is a one-way door, the goal is unclear, it changes documented design or shared rules, or an `agent.A3` trigger holds: run `/akithink` in self-run mode without asking. The interactive session runs only when the owner asks for one.
 
-**Trigger** — match any of the following (case-insensitive): `nạp full`, `load full`, `full load`, `nạp tất cả rule`, `load all rules`, `full akirule`, `nạp hết rule`
+## Full load
 
-**Protocol — execute in order:**
-1. Run `ls ~/.aki/akidevrule/RULE-*.md ~/.aki/akidevrule/METHOD-*.md` to discover the actual file list
-2. Read each file returned (skip anything under `ref-ECC/`)
-3. Emit the `[RULES]` receipt per § Load confirmation, with the loaded set marked `(router:full)`
-
----
+The owner asks, in any wording, to load the whole corpus: `ls ~/.aki/akidevrule/RULE-*.md ~/.aki/akidevrule/METHOD-*.md`, read every file (never `ref-ECC/`), and mark the set `(router:full)` in the receipt.
 
 ## Load confirmation — the `[RULES]` receipt
 
-One line at the start of the response, reporting the **whole rule context**, not this skill's delta:
+One line at the start of the response, reporting the **whole rule context**:
 
 ```
-[RULES] agent,coding,pattern (core) + docs,ui (router) | missing: none
+[RULES] agent,coding,pattern (core) + docs,ui (router)
 ```
 
 | Element | Rule |
 |---|---|
-| Names | topic addresses per the manifest Topic column (`~/.aki/akidevrule/index.md` § addressing scheme). No new vocabulary. |
-| `(core)` | the four `@`-imported files. Always listed, even though this skill did not load them: their presence is otherwise unobservable, and they are the most-violated group. Listing them reports context state; it does not claim credit for the load. |
-| `(router)` | files this skill loaded this turn. Tier 2 writes `(router:full)`. |
-| `(brief)` | for a worker/subagent — the files its spawning prompt named and it actually read. A worker inherits no router, so it uses this instead of `(router)` and emits the line as the first line of its single round (`agent.A5`). |
-| `missing:` | every file that was required and could not be read, else `none`. `[RULES] none \| missing: agent` is the loudest case and the reason this field exists. |
-
-**The line is mandatory.** The session agent emits it on its first response of the session, and again on any turn where the set changes; a worker emits it always. Silence is never "nothing loaded" — a missing line is indistinguishable from a router that never ran, and those are different bugs with opposite fixes. With the line mandatory, a later turn without one carries exactly one meaning: the set is unchanged since the last line printed.
+| Names | topic addresses from the `index.md` manifest Topic column — no new vocabulary |
+| `(core)` | the three core rule files, always listed: their presence is otherwise unobservable |
+| `(router)` | files this router loaded; full load writes `(router:full)` |
+| `(brief)` | a worker/subagent's files named by its spawning prompt and actually read — it inherits no router, and emits the line first in its single round (`agent.A5`) |
 
-The receipt is **self-reported: a diagnostic signal, never evidence** (`agent.B2`). Do not gate closure on it. The cross-check that does carry weight is the agent definition's declared rule manifest against the line it emitted — a mismatch is a finding.
+**Mandatory:** the session agent emits it on its first response and on every turn where the set changes; a worker always. A later turn without one means exactly: set unchanged. The line is self-reported — a diagnostic signal, never evidence of conduct (`agent.B2`).

package/skills/akiship/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: akiship
-description: Full release ritual end-to-end — front-loaded checks, then an unattended pass. ACTIVATION = an imperative turn ordering the release for this repo — the literal token `/akiship`, or an explicit ship/release order ("release trọn vẹn đi", "chạy full release"). A question about it, or a completion word with no release object ("làm cho trọn vẹn"), activates nothing — consult the checklist and answer in chat, read-only. Sequences RULE-release.md B7's checklist under the B8 autonomy contract; the escalation floor, completion-intensity semantics, and push/deploy authorization are owned by B8 and referenced, never restated, here.
+description: Full release ritual end-to-end — front-loaded checks, then an unattended pass. ACTIVATION = the literal token `/akiship`, or an imperative turn, in any language, ordering the release ritual for this repo. A question about it, or a completion word with no release object, activates nothing — consult the checklist and answer in chat, read-only. Sequences RULE-release.md B7's checklist under the B8 autonomy contract; the escalation floor, completion-intensity semantics, and push/deploy authorization are owned by B8 and referenced, never restated, here.
 ---
 
 # akiship — one-command full release
@@ -12,7 +12,7 @@ Invoke with `/akiship` or an explicit release order, only as described in § Act
 **This skill sequences; it owns no content.** The checklist is `RULE-release.md` (B5 migration doctrine, B7 fail-closed gate, B8 autonomy contract, B10 CI, B11 post-deploy verification) and doc sync is `RULE-docs.md`. Both are installed at `~/.aki/akidevrule/`.
 
 1. `Read` `~/.aki/akidevrule/RULE-release.md` IN FULL and `~/.aki/akidevrule/RULE-docs.md` as the FIRST tool calls after this skill loads. Keyword routing, memory of an earlier session, this file's summary, and a rule that happens to be in context do NOT count as loading — only a `Read` performed in THIS run does.
-2. Emit as the first line of the run: `[RULES] agent,coding,pattern (core) + release,docs (akiship) | missing: none`. Any file that could not be read goes under `missing:` and the run STOPS there.
+2. Emit as the first line of the run: `[RULES] agent,coding,pattern (core) + release,docs (akiship)`. If either file could not be read, say so and the run STOPS there.
 3. A run that starts Phase 1 without those two `Read` calls is INVALID: every finding, commit, tag and deploy it produces is unauthorized and MUST be reported as such. Compliance is checked against the tool-call log, never against the receipt line (`agent.B2`).
 
 If a step in this file disagrees with the rule file, the rule file wins — except the activation gate below, which this skill owns outright (`pattern.A1`) and which no rule file, keyword list, or routing table may widen.
@@ -20,7 +20,7 @@ If a step in this file disagrees with the rule file, the rule file wins — exce
 
 ## Activation gate — two conditions, both required, checked before anything else
 
-**1. Release order.** The current user turn carries either the exact token `/akiship`, or a turn explicitly ordering the release ritual for this repo — "release trọn vẹn đi", "ship đợt này luôn", "chạy full release". A completion-intensity phrase with no release object ("làm cho trọn vẹn") activates nothing: it names no ritual, so it is ordinary vocabulary about finishing something, not an order to run this skill. Seeing this file, or `release.B8`, in context is not an invocation either: being loaded is not being called.
+**1. Release order.** The current user turn carries either the exact token `/akiship`, or a turn explicitly ordering the release ritual for this repo, in any wording (worked examples in the table below). A completion-intensity phrase with no release object activates nothing: it names no ritual, so it is ordinary vocabulary about finishing something, not an order to run this skill. Seeing this file, or `release.B8`, in context is not an invocation either: being loaded is not being called.
 
 **2. Imperative, not interrogative** (`agent.A3`). The order alone authorizes nothing — the turn must ask for the run to be *performed*. Where both readings are available, consult.
 

package/skills/akithink/SKILL.md

@@ -1,15 +1,15 @@
 ---
 name: akithink
-description: Structured deep-thinking session between agent and human for important decisions — restate the problem, excavate the goal chain to the ultimate goal, first-principles decomposition (facts/constraints/assumptions), mandatory critique (steelman, inversion, pre-mortem), then converge into a decision record. For big / hard-to-reverse / goal-ambiguous problems — small inline questions are already covered passively by akirule + METHOD-deep-think. Also runnable self-run (non-interactive) when owner-authorized or fired by an `agent.A3` trigger. Recommends running on a top-tier model (Opus/Fable).
+description: Structured deep thinking for decisions — restate the problem, excavate the goal chain to the ultimate goal, first-principles decomposition (facts/constraints/assumptions), mandatory critique (steelman, inversion, pre-mortem), then converge into a decision record. Thinking only: it never edits, runs or ships anything — what happens after the record is decided by the originating turn's class (`agent.A3`), outside this skill. Self-run mode (non-interactive, decide and report) fires on an `agent.A3` deep-think trigger or on owner authorization; trivial two-way-door calls stay inline. Interactive session only when the owner asks for one. Best on a top-tier model (Opus/Fable).
 ---
 
 # akithink — structured deep-thinking session
 
-Invoke with `/akithink`, or when the user explicitly asks for a deep-thinking session on a decision ("let's think this through properly", "hãy tư duy sâu về việc này", "cần một session suy nghĩ kỹ"). This is the **active** consumption mode of `payload/METHOD-deep-think.md` — the same analytical brain that akirule loads passively for ordinary tasks, run here at maximum depth through an interactive protocol.
+The **active** consumption mode of `payload/METHOD-deep-think.md` — the same analytical brain the router loads passively for ordinary tasks, run at maximum depth: interactively when the owner asks for a session, in self-run mode when an `agent.A3` deep-think trigger holds (Invocation scope). It thinks; it never acts (`pattern.A3`).
 
 ## When NOT to use this skill
 
-Small, reversible, low-cost-of-error decisions should just be decided. Casual "should we…?" questions are already handled inline by akirule auto-loading `METHOD-deep-think.md` passively — that is enough for two-way-door decisions. Reach for `/akithink` only when the decision is big, hard to reverse (one-way-door), or the goal itself is still unclear. Do not open a session for something that a one-paragraph answer would resolve.
+Trivial, reversible execution with nothing to decide gets no session — act. An interactive session is reserved for a decision the owner wants to reason through together; a decision that meets an `agent.A3` trigger runs in self-run mode (see Invocation scope), scaled in depth to how hard the decision is to reverse; a two-way-door call is decided inline.
 
 ## Toolbox
 
@@ -50,18 +50,19 @@ Then:
 ## Interaction rules
 
 - **Pacing:** ask 1–2 highest-value questions per turn. `AskUserQuestion` is fine for discrete choices. Never dump a full questionnaire in one turn.
-- **Escape hatch:** the user can say "chốt" (or an equivalent "let's converge/decide now") at any point to jump straight to Phase 5 with whatever has been established so far.
+- **Escape hatch:** the user can ask to converge or decide now, in any wording, at any point to jump straight to Phase 5 with whatever has been established so far.
 - **Anti-sycophancy:** same rule as METHOD Module 3 — do not agree without critique, in any phase.
 - **Anti-overuse guard:** if the problem turns out to be small and reversible once restated in Phase 1, say so and offer to just decide it directly instead of running the full protocol.
 
 ## Self-run mode
 
-Runs all phases without waiting, when the owner authorizes the agent to run it itself (e.g. "tự nạp /akithink", "tự chốt", "cho bạn tự quyết") or when fired by an `agent.A3` deep-think trigger:
+Runs all phases without waiting, when the owner authorizes the agent to decide on its own, in any wording, or when fired by an `agent.A3` deep-think trigger:
 - Phase 1 restatement is written, not confirmed.
 - The Interaction rules pacing (1–2 questions per turn) does not apply — no questions are asked mid-session.
 - Questions reach the owner only via `agent.A3`'s escalation outcomes, never through this skill's own turn-by-turn interaction.
-- Phase 5 converges, acts, and reports the decision block (`agent.A3`'s converged outcome). A decision-record doc per `RULE-docs.md` still applies when the decision is durable.
+- Phase 5 converges and reports the decision block (`agent.A3`'s converged outcome), and the session ends there. This skill thinks and never acts (`pattern.A3`): whether anything is then executed is decided by the class of the originating turn — a task turn proceeds under `agent.A3`, a question turn gets the block and nothing else. A decision-record doc per `RULE-docs.md` still applies when the decision is durable.
 
 ## Invocation scope
 
-Interactive mode is explicit-invoke only — akirule does not auto-trigger the interactive protocol; it is reached only when the user asks for it by name or in equivalent words. Self-run mode above is the exception: it fires from an `agent.A3` trigger or owner authorization, without an explicit `/akithink` invocation. The signals that matter for passive-mode auto-loading live on `METHOD-deep-think.md`.
+- **Self-run — model-invoked, no confirmation.** Fires on an `agent.A3` deep-think trigger (that list is the only trigger list — not restated here), on the router's deep-think-depth line (`akirule`), or on owner authorization. Two-way-door work stays below it: decide inline with `METHOD-deep-think.md` passively.
+- **Interactive — owner-invoked only**, by name or in equivalent words; never auto-started, because it spends the owner's turns.

package/skills/akiflow/scripts/council-cost.sh

@@ -1,4 +0,0 @@
-#!/usr/bin/env bash
-# Transitional Unix wrapper — the Python file is the SSOT (cross-platform, incl. Windows).
-# Kept so existing prompts/docs that name "council-cost.sh" keep working on Unix during the transition.
-exec python3 "$(dirname "$0")/council_cost.py" "$@"

package/skills/akiflow/scripts/council-open.sh

@@ -1,4 +0,0 @@
-#!/usr/bin/env bash
-# Transitional Unix wrapper — the Python file is the SSOT (cross-platform, incl. Windows).
-# Kept so existing prompts/docs that name "council-open.sh" keep working on Unix during the transition.
-exec python3 "$(dirname "$0")/council_open.py" "$@"

package/skills/akiflow/scripts/council-read.sh

@@ -1,4 +0,0 @@
-#!/usr/bin/env bash
-# Transitional Unix wrapper — the Python file is the SSOT (cross-platform, incl. Windows).
-# Kept so existing prompts/docs that name "council-read.sh" keep working on Unix during the transition.
-exec python3 "$(dirname "$0")/council_read.py" "$@"

package/skills/akiflow/scripts/council-verify.sh

@@ -1,4 +0,0 @@
-#!/usr/bin/env bash
-# Transitional Unix wrapper — the Python file is the SSOT (cross-platform, incl. Windows).
-# Kept so existing prompts/docs that name "council-verify.sh" keep working on Unix during the transition.
-exec python3 "$(dirname "$0")/council_verify.py" "$@"

package/skills/akiflow/scripts/scythe.sh

@@ -1,4 +0,0 @@
-#!/usr/bin/env bash
-# Transitional Unix wrapper — the Python file is the SSOT (cross-platform, incl. Windows).
-# Kept so existing prompts/docs that name "scythe.sh" keep working on Unix during the transition.
-exec python3 "$(dirname "$0")/scythe.py" "$@"