@yunhozz/arc 0.1.2 → 0.1.4

package/claude/skill/SKILL.md

@@ -18,8 +18,7 @@ same-task rechecks may reuse.
 Follow user instructions and project guidance. Orchestrator uses the current chat model and answers a simple,
 self-contained question (answerable from context or one quick read, no edits) directly.
 For substantive multistep work, Orchestrator coordinates implementation, configuration, tests, and mixed work.
-Assign material
-research/analysis and bounded read-only exploration of static code, documents, data, and logs/reports to Scouter.
+Assign material research/analysis and bounded read-only exploration of static code, documents, data, and logs/reports to Scouter.
 Orchestrator handles research directly when the needed material is already in its context or the check is a quick read
 of a few known
 files; all other material research/analysis and bounded exploration goes to Scouter with its configured settings (a
@@ -29,85 +28,6 @@ are not standalone document writing (see Role gate).
 For mixed research/document requests, Orchestrator may explicitly assign only research to Scouter.
 Live execution-state investigation or cleanup are outside Scouter scope and this boundary makes no owner assignment.
 
-## Ownership
-
-- Orchestrator: sole owner of development, configuration, tests, implementation-dependent documentation, and mixed tasks
-  requiring implementation, assigning their edits to Coder. Coordinates scope, planning, approvals, integration,
-  acceptance, verification, and
-  completion.
-- Scouter: read-only material research/analysis and assigned static code/document/data/log exploration. Reports
-  evidence, assumptions, unresolved questions, impact, next actions, and workspace/path issues to Orchestrator.
-  Does not edit
-  files or author standalone document files, and does not decide design/plans, verification, review, or completion.
-- Planner: returns design/spec/plan drafts.
-- Coder edits assigned, approved implementation/configuration/test-code files and assigned dependent docs.
-  Orchestrator does not edit
-  them directly except under the Orchestrator direct path for small tasks.
-- QA: verifies without edits.
-- Reviewer: independently reviews the final full change.
-- All five roles report directly to Orchestrator at depth 2: Scouter, Planner, Coder, QA, and Reviewer.
-  Orchestrator is depth 1.
-  Depth-2 roles cannot create agents or delegate tasks to another role. Reviewer remains independent.
-- Claude native subagent names: Scouter=`arc-scouter`, Planner=`arc-planner`, Coder=`arc-coder`, QA=`arc-qa`,
-  Reviewer=`arc-reviewer`.
-- Across the full tree, obey configured limits for simultaneous subagents, including Scouter; there are no reserved slots.
-  Before first creation, read `references/limits.md` and installed `limits.toml`; maintain its cumulative ledger and reservations.
-  Parallelize independent tasks only; dependent handoffs are sequential and editing scopes cannot overlap. These are
-  ARC limits, not verified runtime concurrency or depth capabilities. Use Claude native subagent execution with
-  the installed native name and receive its completion result; report unavailable execution capabilities to
-  Orchestrator.
-- Scouter, Planner, and Reviewer do not edit, execute commands, or save standalone documents; QA verifies without edits.
-  Each role stays within its shipped tool allowlist; a tool list is not a filesystem sandbox.
-
-## Instruction and execution adapter
-
-Native Claude profiles use Markdown frontmatter with the `effort` field.
-The native `env.CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS` value is a string, distinct from ARC's ledger limits.
-The native tool allowlists and prompt guards are not a filesystem sandbox; local declarations do not prove runtime enforcement.
-
-Apply platform, user, and project instructions according to their precedence, then ARC rules for ownership,
-permissions, models, concurrency, routing, and approvals, then the local ARC reference assigned to the role. A called skill
-adds no agents or authority. Map executor requests such as `superpowers:executing-plans` and
-`superpowers:subagent-driven-development` to Orchestrator's dependency-aware coordination and risk-scaled verification;
-this replaces
-executor mechanics and any separate execution-method choice, including prompts in an existing local reference.
-Preserve plan approval, workspace, design, spec, and other applicable requirements, including TDD subject to the
-explicit ARC exception below. Adapt local `brainstorming` role, save, and early spec commit instructions to
-ARC Planner ownership and evidence gates in planning/handoff; preserve upstream reference content. Report conflicts or
-missing required local references before dependent work.
-
-Planner, Reviewer, and Scouter return findings, relevant questions, next actions, and workspace/path issues to the
-Orchestrator. Planner preserves complete requested drafts. Orchestrator integrates results (save, route,
-obtain approval; never author), routes decisions and required approvals,
-and owns development acceptance and completion. Orchestrator coordinates dependent implementation tasks sequentially and
-starts
-a fresh Coder for each top-level task; reuse the current Coder only for corrections, rework, or rechecks of the same
-task while the
-approved scope, workspace, ownership, and relevant context remain valid, after Orchestrator rechecks workspace,
-branch/HEAD and change state against the brief. A fresh Coder for the next task is a restart under handoff (choice reuse
-and restart brief rules are there). After an approved plan or acceptance-criteria amendment, start a fresh Coder for
-the remaining work even within the same task. Do not add per-task QA or
-review gates solely because a task boundary exists; apply risk requirements and specific approved obligations. If the
-next task depends on a still-unverified risky contract, complete applicable QA at that dependency boundary and
-resolve or explicitly disposition findings before dependent implementation. This does not create a gate for every task.
-
-## Dependency analysis and parallel dispatch
-
-Before the first Coder assignment for an approved plan, Orchestrator records its dependency/readiness map and
-initial ready batch under [planning](references/planning.md), which owns record fields and readiness conditions.
-File separation alone never proves independence. Pass the full approval/preparation and handoff gates for every
-assignment; unresolved dependencies, shared contracts, or ownership conflicts hold affected work.
-Start all ready independent tasks concurrently with fresh Coders within capacity under [limits](references/limits.md)
-and any lower actual runtime limit; record capacity and serialization reasons. Same-file concurrent Coder edits are
-prohibited, even on different lines. ARC's cap is not a claim of runtime capability.
-
-Reassess readiness after completion reports, new check evidence, acceptance, commit, slot return, or a new conflict.
-Coder completion alone does not release dependents: require predecessor checks, Orchestrator acceptance and verified
-focused commit, or accepted no-change evidence under [commit](references/commit.md). Start newly ready tasks without
-waiting for unrelated batch members; failures hold affected dependents while unaffected ready work may continue.
-Preserve risk-scaled QA/Reviewer timing and execution-target restrictions. Shared-checkout Git coordination belongs to
-commit.md; refresh assignment evidence under [handoff](references/handoff.md).
-
 ## Shared terms
 
 The handoff, git-recovery, and commit references and the Coder profile use these terms; context-specific commands,
@@ -136,235 +56,34 @@ Do not load all references on every task.
 
 | Reference | Required before |
 |---|---|
-| [planning](references/planning.md) | Design/plan-depth judgments, spec/plan drafting or approval, first spec/plan save |
+| [coordination](references/coordination.md) | Before the first specialist creation or assignment and related coordination decisions; role contracts, briefing, adapters, models and token discipline |
+| [limits](references/limits.md) and installed `limits.toml` | Before the first specialist creation; capacity, reservations and cumulative ledger |
+| [planning](references/planning.md) | Design/plan-depth judgments, spec/plan drafting or approval, first spec/plan save; dependency and readiness decisions before assignment |
 | [handoff](references/handoff.md) | Every Coder first start/restart preparation by Orchestrator, and before each Orchestrator direct edit's first edit; Coder trusts the Orchestrator-verified brief under its profile and reads only brief-cited sections |
 | [handoff-prep](references/handoff-prep.md) | Execution-target choice request, each preparation Git mutation (branch creation/switch, staging, commit) |
 | [commit](references/commit.md) | Plan-task acceptance and its focused commit, resuming a task with an unclear commit result |
-| [verification](references/verification.md) | Orchestrator's verification design, QA/Reviewer assignment, correction rechecks, UI acceptance checks; QA and Reviewer use their profiles and only brief-cited sections |
+| [verification](references/verification.md) | Orchestrator's verification design, QA/Reviewer assignment, correction rechecks, UI acceptance checks, risk classification, acceptance and completion;  QA and Reviewer use their profiles and only brief-cited sections |
 | [git-recovery](references/git-recovery.md) | Branch collision, Git preparation failure, partial completion, metadata write denial recovery |
 | [visual-companion](references/visual-companion.md) | Visual companion offer or operation |
 
-Design and plan depth are independent of verification risk. Planner alone uses local brainstorming/writing-plans
-(Role gate);
-Orchestrator integrates complete drafts and obtains applicable approvals. Architectural specs and Bounded written specs
-required by Orchestrator's recorded plan-depth judgment use planning save gates; a required plan alone does not require
-a spec. Obtain explicit execution-target choice and verify actual target preparation before formal drafting
-and saving. Complete all current-scope individual document approvals before the batch docs commit. A missing required skill blocks its stage.
+Before classifying a small-task, plan-omission, or TDD exception, read the full conditions in [handoff](references/handoff.md), including Coder TDD and constraints and Orchestrator direct path for small tasks; read [planning](references/planning.md) for design/plan-depth judgments and [verification](references/verification.md) for the full risk criteria before deciding eligibility. An exception name or this index alone never establishes eligibility.
 
-## Common handoff gate
-
-Before every Coder first start/restart, Orchestrator passes the full gate in
-[handoff](references/handoff.md): applicable approvals/artifacts or valid omissions, explicit execution-target choice
-or verified reuse, intended accessible repository/workspace, actual Git identity/state, preservation/ownership,
-verified document commits or valid absence, and no unresolved failure/partial completion.
-Missing evidence, mismatches, unclear ownership or unresolved preparation block handoff and require Orchestrator
-resolution and full revalidation. Handoff owns the evidence fields, canonical handoff record, restart brief, choice lifetime
-and reuse. Coder trusts the Orchestrator-verified brief and reports actual conflicts under its self-contained profile;
-never replace its local guards with a requirement to load Orchestrator procedures.
-Depth-2 roles use the supplied workspace and report path/state conflicts; they cannot create/switch workspaces or
-branches. The same conditions apply before a Orchestrator direct edit.
-Claude v1 supports the current checkout only; obtain the explicit current-branch or task-branch choice and complete
-approved document preparation under [handoff-prep](references/handoff-prep.md).
-ARC-managed worktree execution is unsupported; report an isolated worktree request before dependent work.
-
-## Coder TDD and constraints
+## Ownership
 
-Before feature, bug-fix, or behavior edits, Coder follows local `test-driven-development` unless the explicit
-ARC exception applies; the Coder profile holds Coder's full TDD rules. TDD is waived only when every small,
-low-risk criterion (Risk-scaled execution) and every plan-skip criterion (Orchestrator direct path) holds.
-Before Coder starts,
-Orchestrator records the scope, why every criterion is met, acceptance criteria, and focused verification in the brief.
-An explicit user or task-specific TDD request overrides
-this waiver. For qualifying tasks only, this exception takes precedence over the generic trigger in the local reference;
-do not change that skill. Ordinary multi-step or significant/high-risk work is not eligible. The waiver skips only
-RED-GREEN steps; focused checks and risk-appropriate QA/Reviewer remain, and do not claim TDD was followed.
-If a constraint blocks a required TDD step, Orchestrator records the
-decision in the brief/plan and obtains any required human approval; internal approval is not a substitute.
-Non-behavior documentation/configuration uses only a specifically authorized exception recorded in the brief; do not
-generalize it to behavior work.
+Read [coordination](references/coordination.md#ownership) before assigning roles. Only Orchestrator accepts work; specialists report directly at depth 2 and cannot delegate.
 
 ## Risk-scaled execution
 
-Orchestrator assigns edits exclusively to Coder except under the Orchestrator direct path below, and determines affected
-behavior, risk,
-and smallest meaningful verification.
-
-| Risk | Minimum flow |
-|---|---|
-| Small, low risk | Coder, or Orchestrator direct path → Orchestrator's focused checks → acceptance |
-| Ordinary behavior | Coder → independent QA → acceptance |
-| Significant/high risk | Coder → QA → independent Reviewer of the final full change → acceptance; with a plan, each plan task Coder → FRESH QA → acceptance/commit satisfies the QA step, then independent Reviewer once on the final full change after all plan tasks |
-
-Ordinary and significant plan tasks need a FRESH QA before acceptance; only small, low-risk tasks may be accepted on
-Orchestrator focused checks. Small, low risk means narrow, understood, readily reversible, and verifiable by focused
-checks. Ordinary behavior
-fails those conditions without a significant-risk trigger. Significant risk includes shared role/behavior contracts,
-shared state, lifecycle/integration order, security/permissions, data loss/migration, public interfaces, or costly
-installation/deployment/rollback. Substantial behavior or contract changes are significant regardless of file count.
-Unclear risk requires
-investigation or the higher flow. Environment failure does not waive checks or determine design depth.
-
-Do not add per-task gates automatically. Reviewer is never a plan-task acceptance prerequisite; for significant work
-with a
-plan, it reviews the final full change once after all plan tasks are accepted with their risk-scaled checks,
-following the last plan task's required checks and any QA recheck at the final relevant state; significant work without
-a plan
-keeps Reviewer after QA before acceptance. Preserve specific approved obligations and complete risky dependency checks
-before dependent implementation. Reuse evidence only when scope, relevant state, independence, freshness, and flow
-position satisfy each covered requirement; changes, failures, or missing/conflicting evidence invalidate affected reuse.
-QA checks independently without edits; Reviewer independently reads the final full change after QA for significant
-work, without QA, planning, edits, delegation, or completion decisions. Orchestrator routes fixes to Coder,
-obtains affected QA rechecks outside the final plan Reviewer correction exception and required final review, and accepts after findings/evidence gaps are resolved or
-explicitly dispositioned.
-
-Criterion verdicts follow the Evidence verdict.
-
-### Final plan Reviewer correction loop
+Read [verification](references/verification.md#risk-scaled-execution) before risk classification, verification design, assignment or acceptance. It holds the risk table, risk definitions, evidence-reuse rule and role order.
 
-For a plan's final overall Reviewer findings, including behavior findings, Orchestrator assigns
-Coder → Reviewer recheck with no QA reassignment. Repeat corrections and Reviewer rechecks until findings are resolved;
-the initial single full review does not prohibit necessary rechecks. Before the initial final overall Reviewer,
-risk-required checks and QA execution failures or unmet criteria still require Coder correction → QA recheck.
-This exception applies only to findings from the final overall Reviewer of work with a plan.
-Work without a plan retains its existing verification flow. Scope expansion, separate mandatory obligations,
-or unresolved evidence gaps hold affected work for Orchestrator to resolve and obtain required approvals.
-Orchestrator assigns corrections/rechecks and decides acceptance. Reviewer remains read-only, must not run QA
-checks or decide acceptance. Previous QA evidence must not be presented as post-fix execution evidence;
-report only checks actually performed, their actor, target state, results and remaining limits.
-
-Read verification for evidence fields, failure/finding flow, UI permissions, cleanup and acceptance reporting.
-
-Authorization evidence and probe/combined scope are owned by [planning](references/planning.md#authorization-and-scope);
-valid reuse and actual-state refresh by [handoff](references/handoff.md#authorization-continuity).
-After gates hold, continue approved no-doc scope through required checks and Orchestrator acceptance under
-[verification](references/verification.md#completion-continuity); a role report alone does not complete the work.
-
-## Orchestrator direct path for small tasks
-
-Orchestrator may edit directly only when every small, low-risk criterion (Risk-scaled execution) holds.
-Every plan-skip criterion must also hold: one local change, no dependent stages, no cross-component shared state,
-lifecycle, or integration-order concerns, and one focused verification path. Significant, architectural,
-ordinary-behavior, unclear-risk work and edits overlapping a running Coder's assigned files are ineligible.
-
-Significant risk is defined in Risk-scaled execution and excludes work from the Orchestrator direct path;
-do not infer eligibility from a small file count.
-
-Before editing, Orchestrator records a scope record (not a brainstorming design) with scope and files,
-why every criterion holds, acceptance criteria, and focused verification. Apply authorization in
-[planning](references/planning.md#authorization-and-scope): an existing sufficiently specific user request can approve
-that scope; no duplicate approval is needed. Otherwise present the scope record to the user and obtain explicit
-approval before editing. Silence, an ambiguous response, or approval of other work is not approval.
-Orchestrator then verifies the same handoff gate as a Coder first start: explicit execution-target choice or valid
-reuse, accessible intended workspace and repository, branch or detached HEAD, HEAD, staged/unstaged/untracked state,
-preservation and ownership, and no unresolved failure or partial completion. Read the [handoff](references/handoff.md)
-and [handoff preparation](references/handoff-prep.md) references before checking this gate.
-
-Orchestrator edits only the approved files, preserves others' edits, and makes surgical changes without unrelated
-refactoring or unapproved dependencies. Behavior edits follow the Coder TDD rules and applicable recorded waiver
-criteria; an explicit user or task-specific TDD request still requires test-driven-development.
-Do not claim TDD under a waiver. After editing, Orchestrator records changed files, runs focused checks,
-connects each acceptance criterion to evidence, and reports unverified scope. Orchestrator is not an independent
-reviewer of its own edits; assign QA when evidence is incomplete. If scope expands, risk becomes unclear,
-or any criterion fails, stop editing, record completed changes, and return subsequent edits to the normal Planner/Coder
-flow. A failed focused check or a QA finding routes the correction to Coder, and it is rechecked; Orchestrator does not
-self-correct.
-
-Like other plan-skip
-paths, there is no automatic task commit; commits follow applicable guidance and user requests.
-
-## Automatic commit after plan-task acceptance
-
-Orchestrator accepts each approved top-level task by its own judgment and immediately creates one focused local commit
-for that
-task without additional user commit approval. Read [commit](references/commit.md) before the acceptance and commit.
-Push, merge, publish, deploy, and install still follow their separate guidance and approval rules.
-
-## Token discipline and handoffs
-
-- Only Orchestrator invokes Claude native subagents or assigns specialist tasks. Give each invocation a descriptive role
-  and bounded objective; the installed native profile determines its role and local model declarations.
-
-- Keep one shared brief with fixed field order: Goal; Criteria (IDs); Exact scope/ownership (absolute workspace,
-  branch or detached HEAD and HEAD, handoff record path, when one exists, files);
-  Constraints/decisions; Evidence (paths/lines, commands, artifact links); Prior findings; Exact next objective (one
-  bounded objective); Return format (conclusion, evidence locations, unresolved points, next step).
-  On follow-ups send only changed fields and mark the rest `unchanged` (relative to a brief the recipient received);
-  restart briefs follow handoff; a fresh specialist gets every other field in full. Send only the
-  self-contained subset needed by the next role and links to accessible artifacts; omit full history, repeated
-  instructions, and raw logs. No findings may be brief; requested deliverables such as complete plan drafts remain
-  complete. Cite paths/lines/pages/commands/links instead of logs; investigate gaps only.
-- `AskUserQuestion` questions use only `question`, a `header` of at most 12 characters, 2-4 `options` each with `label`
-  and `description`, and `multiSelect`.
-- Always start an ARC role by its installed native name (`arc-*`) with only the supplied scoped brief;
-  never use a context-inheriting fork (such as the `fork` subagent type) for an ARC role; do not claim fresh context
-  isolation without evidence. Reuse an existing specialist for related follow-up with only changed facts/objective when
-  its context
-  remains relevant; start fresh for unrelated or bloated context. Coder and QA freshness follow the Role gate.
-- Cite in the brief the absolute path of each required local ARC reference's SKILL.md (`test-driven-development` for Coder,
-  `brainstorming`/`writing-plans` for Planner); the role Reads it before dependent work.
-- For Reviewer, Orchestrator writes the final base..HEAD diff plus changed-file list to
-  `<git-common-dir>/arc/review/<slug>.diff` (same slug as the handoff record; base is the approved base HEAD recorded at
-  handoff; inline when small or write denied) and cites its absolute path in the brief; Reviewer reads it and states
-  limits. See verification.
-- In Coder briefs, cite the plan/spec path with the task section's line range and include only the needed excerpts,
-  acceptance criteria, and constraints; do not ask Coder to read whole plans or specs.
-- Before optional calls, name the unresolved question and expected artifact; skip calls already resolved by available
-  evidence/direct inspection.
-- Run each ARC role as a foreground Agent call and use its returned result, or run it in the background and wait for the
-  completion notification; report unavailable execution to Orchestrator rather than inventing an API.
-  Do not poll status in loops; never sleep-poll. A timeout or delay is not a reason to poll or check status in between.
-  Send one complete brief per objective and batch related corrections. For long Bash commands set a sufficient `timeout`
-  or use `run_in_background` and wait for its completion notification.
-
-- Read only the needed ranges of files and outputs (for example `rg -n`, `sed -n`, `head`/`tail`) and cap long command
-  output. Do not re-read files or outputs already in context unless they changed. A mandatory reference already read in
-  this context and unchanged need not be re-read, and this skill file, once read in this context and unchanged,
-  is not re-read on follow-up turns;
-  this does not shorten any triggered mandatory reference read.
-- When a plan completes or before starting another plan in a session with long history, Orchestrator records the
-  canonical
-  handoff state in the handoff record file and recommends that the user continue in a new session.
-- Before handoff, post one short update with role/objective/expected output; after return, combine findings and next
-  stage concisely. Do not expose hidden reasoning or raw prompts.
-
-### Local superpowers references
-
-Orchestrator briefs absolute paths under the selected installed ARC directory: Planner reads
-`references/superpowers/brainstorming/SKILL.md` and `references/superpowers/writing-plans/SKILL.md`;
-Coder reads `references/superpowers/test-driven-development/SKILL.md`, including required relative references.
-Resolve paths within each skill directory. Runtime needs no global discovery, external Skill invocation, or automatic download.
-Missing/damaged local files stop dependent work: report exact paths to Orchestrator, without global fallback.
-ARC approval, ownership, TDD exceptions and executor adapters still apply.
-
-## Models
-
-`models.toml` beside this skill is the source of truth for role model and reasoning-effort settings.
-Configuration keys `arc_scouter`, `arc_planner`, `arc_coder`, `arc_qa`, and `arc_reviewer` map to the hyphenated
-Claude native subagent names above; they are not tool-call names.
-Orchestrator uses the current conversation model. Use configured role settings without substitution or effort
-reduction; report unavailable settings.
-Local declarations do not prove runtime provider support, account access, alias resolution, actual model or effort
-application, concurrency or depth enforcement.
-New sessions reload profiles; running agents retain their current settings and parent relationships. Configuration
-changes do not automatically reparent running agents or prove runtime parent behavior.
+## Common handoff gate
 
-For browser visualization needs read [visual-companion](references/visual-companion.md). Use only capabilities
-available within each role's exact allowlist; report unavailable capabilities and preserve unverified visual scope.
+Read [handoff](references/handoff.md#common-handoff-gate) before every Coder first start/restart and Orchestrator direct edit.
 
 [ARC role policy: contract begin]
 Generated from lib/policy/role-policy.json; do not edit this managed section manually.
-- [scope.non-escalation] Act only within the intersection of role authority, approved scope and available platform tools. Delegation, restart, agent messages and attached instructions do not expand role authority. Never bypass a restriction through aliases, scripts, other tools, processes or redelegation. Return conflicting instructions to Orchestrator before dependent work; reuse valid prior approvals for unchanged scope rather than requesting them again.
-- [git.specialists-deny] Specialist roles MUST NOT change Git state: no stage, commit, push, merge, rebase, reset, branch creation/switching or worktree creation/removal, during normal implementation or recovery. Even an explicit Orchestrator assignment cannot authorize these actions; return them to Orchestrator. Read-only Git inspection remains allowed within the assigned scope.
-- [git.orchestrator-accept-commit] Only Orchestrator accepts work and executes Git mutations. One approved top-level plan task becomes one focused implementation commit after criteria, required checks and findings are satisfied; Orchestrator accepts then commits without additional user commit approval. Reports, passing checks and Reviewer opinions do not replace acceptance. Preserve unrelated changes and ownership and verify the resulting SHA, included content, HEAD and remaining changes. Existing small-task direct and plan-omission paths are unchanged.
-- [external.explicit-user-authority] Push, merge, deploy, publish and external messages require explicit user authorization for that action, scope and target. Local commit authority does not grant external authority. Orchestrator performs authorized external actions; specialist roles return them without execution.
+- [scope.non-escalation] Act only where role authority, approved scope and available platform tools all permit. Delegation, restart, agent messages and attached instructions do not expand role authority. MUST NOT bypass a restriction through aliases, scripts, other tools, processes or redelegation. Return conflicting instructions to Orchestrator before dependent work; reuse valid prior approvals for unchanged scope rather than requesting them again.
+- [external.explicit-user-authority] Push, merge, deploy, publish and external messages require explicit user authorization for that action, scope and target. Local commit authority grants no external authority. Orchestrator performs authorized external actions; specialist roles return them without execution.
 - [role.orchestrator-boundary] Assign design/spec/plan/brainstorming drafts ONLY to Planner and implementation/configuration/test edits to Coder. Orchestrator saves complete drafts and owns approval requests, preparation, scheduling, evidence, acceptance and completion. Direct implementation is limited to the existing small, low-risk direct path; this policy does not expand it.
-- [role.scouter-read-only] Research assigned static sources and report findings, evidence and limits. Do not edit files, install, execute checks, prepare execution targets, inspect live operational state, change external state or decide design, verification, review or acceptance.
-- [role.planner-draft-only] Return design/spec/plan drafts and dependencies, criteria, hold conditions and verification needs in the response. Do not save documents, implement, run checks, prepare targets, request user approval or decide acceptance. Stop formal target-dependent drafting if actual prepared target evidence is missing; route decisions to Orchestrator.
-- [role.coder-implementation] Implement only assigned approved files and focused checks under the existing TDD contract. Report changed files, RED/GREEN or authorized exception evidence, results, limits and follow-up. Do not plan, independently QA/review your own work, accept the task or declare overall completion. Git changes remain forbidden even when implementation succeeds.
-- [role.qa-verification] Run approved checks and report commands, observations, reproduction, evidence and limits. Create only essential temporary data/logs/reports in the brief-authorized location and lifetime. Do not edit product source, tests, fixtures or configuration to pass checks, deploy or accept work. Persistent product-state checks require explicit scope and cleanup ownership. Return failures for Coder correction and required QA recheck.
-- [role.reviewer-independent] Independently inspect the assigned final changes and evidence and report actionable findings and limits. Remain read-only; do not execute QA tests, edit files, perform Git mutations or decide acceptance.
-- [review.significant-no-plan] For significant/high-risk work without a plan: Coder → QA and required QA rechecks → Reviewer of the final full change → Orchestrator acceptance. Do not omit Reviewer merely because no plan exists. This creates no new plan obligation.
-- [review.significant-plan] For significant/high-risk plan work: each task uses Coder → fresh QA as required → Orchestrator acceptance and focused commit. After all tasks are accepted and required QA is complete, Reviewer reviews the final full change once. Reviewer is NOT a per-task or per-commit required gate. Preserve required checks and necessary finding rechecks.
-- [review.final-plan-recheck] For final overall Reviewer findings on plan work, including behavior findings, use Coder → Reviewer without QA reassignment; repeat until resolved. This exception applies only to that final plan stage. Preserve required QA and QA failure rechecks before initial final review and outside this exception.
 - [platform.claude] Existing per-role tool allowlists reduce available tools; Bash and role contracts are not a filesystem sandbox. A role-scoped Git guard is a separate integration and is not supplied by these policy sections alone.
 [ARC role policy: contract end]

package/claude/skill/hooks/role-git-guard.mjs

@@ -1,89 +1,9 @@
 import fs from 'node:fs';
 import {pathToFileURL} from 'node:url';
 
-const deny = reason => ({allowed:false,reason});
-const isGit = word => /(?:^|[\\/])git(?:\.exe)?$/i.test(word);
-export function validateGitPolicy(policy) {
-  if (!policy || policy.schemaVersion !== 1 || !Array.isArray(policy.globalValueOptions) || !Array.isArray(policy.globalFlags) || !policy.commands || typeof policy.commands !== 'object' || Array.isArray(policy.commands)) throw Error('Invalid Git policy');
-  const strings = list => Array.isArray(list) && list.every(x=>typeof x === 'string' && x.startsWith('-'));
-  if (!strings(policy.globalValueOptions) || !strings(policy.globalFlags) || !Object.keys(policy.commands).length) throw Error('Invalid Git policy');
-  for (const rule of Object.values(policy.commands)) if (!rule || !strings(rule.flags) || !strings(rule.values) || !['any','none','query','list'].includes(rule.positionals)) throw Error('Invalid Git command policy');
-  return policy;
-}
-// This deliberately supports a small shell grammar, rather than executing a shell.
-function tokenize(command) {
-  const tokens=[]; let word='', started=false, quote=null;
-  for(let i=0;i<command.length;i++) {
-    const char=command[i];
-    if(char==='\\' && /[\r\n]/.test(command[i+1]??'')) throw Error('Escaped line terminator');
-    if(quote) {
-      if(char===quote){quote=null;continue;}
-      if(quote==='"' && /[$`]/.test(char)) throw Error('Dynamic shell syntax');
-      // Preserve Windows paths in quoted executable names.
-      if(char==='\\' && quote==='"' && /["\\$`]/.test(command[i+1]??'')){word+=command[++i];continue;}
-      word+=char;continue;
-    }
-    if(char==='"'||char==="'"){quote=char;started=true;continue;}
-    if(/[\r\n\x00<>`$(){}&]/.test(char) && !(char==='&'&&command[i+1]==='&')) throw Error('Unsupported shell syntax');
-    if(char===';'||char==='|'||char==='&') {
-      if(started){tokens.push(word);word='';started=false;}
-      const operator=command.slice(i,i+2); if(operator==='&&'||operator==='||')i++;
-      tokens.push({operator:operator==='&&'||operator==='||'?operator:char});continue;
-    }
-    if(/\s/.test(char)){if(started){tokens.push(word);word='';started=false;}continue;}
-    if(char==='\\') {if(i+1>=command.length)throw Error('Incomplete escape'); word+=command[++i];started=true;continue;}
-    if(char==='#')throw Error('Unsupported shell comment');
-    word+=char;started=true;
-  }
-  if(quote)throw Error('Unclosed quote'); if(started)tokens.push(word);return tokens;
-}
-function classifyWords(words,policy,depth) {
-  if(!words.length)return deny('Empty shell segment');
-  const executable=words[0].split(/[\\/]/).at(-1).toLowerCase();
-  if(['sh','bash','sh.exe','bash.exe'].includes(executable)) {
-    if(depth>=4 || words.length!==3 || words[1]!=='-c')return deny('Unsupported shell wrapper');
-    return classifyGitCommand(words[2],policy,depth+1);
-  }
-  if(!isGit(words[0]))return words.some(isGit)?deny('Unsupported indirect Git invocation'):{allowed:true};
-  let i=1;
-  while(i<words.length && words[i].startsWith('-')) {
-    const option=words[i++],equal=option.indexOf('='),key=equal<0?option:option.slice(0,equal);
-    if(policy.globalFlags.includes(option))continue;
-    if(!policy.globalValueOptions.includes(key))return deny('Unknown Git global option');
-    if(equal<0 && (i>=words.length || words[i++].startsWith('-')))return deny('Missing Git option value');
-    if(equal>=0 && !option.slice(equal+1))return deny('Missing Git option value');
-  }
-  const combined=`${words[i]} ${words[i+1]}`;
-  const name=Object.hasOwn(policy.commands,combined)?(i+=2,combined):words[i++];
-  const rule=Object.hasOwn(policy.commands,name)?policy.commands[name]:null; if(!rule)return deny('Git mutation or unknown subcommand');
-  let positions=0,query=false,list=false,paths=false;
-  for(;i<words.length;i++) {
-    const arg=words[i];
-    if(arg==='--' && rule.positionals==='any'){paths=true;continue;}
-    if(!paths && arg.startsWith('-')) {
-      if(/^-[0-9]+$/.test(arg)&&rule.flags.includes('-<count>'))continue;
-      const equal=arg.indexOf('='),key=equal<0?arg:arg.slice(0,equal);
-      if(rule.values.includes(key)) {if(equal<0 && (i+1>=words.length||words[++i].startsWith('-')))return deny('Missing query option value'); if(equal>=0&&!arg.slice(equal+1))return deny('Missing query option value');continue;}
-      if(!rule.flags.includes(arg))return deny('Unknown or mutating Git option');
-      if(['--get','--get-all','--get-regexp','--list','-l'].includes(arg))query=true;
-      if(['--list','-l','--show-current'].includes(arg))list=true;
-    } else positions++;
-  }
-  if(rule.positionals==='none'&&positions || rule.positionals==='query'&&(!query||positions>1) || rule.positionals==='list'&&positions&&!list)return deny('Git write or unsupported arguments');
-  return {allowed:true};
-}
-export function classifyGitCommand(command,policy,depth=0) {
-  try {
-    validateGitPolicy(policy);
-    if(typeof command!=='string'||!command.trim())return deny('Missing shell command');
-    const tokens=tokenize(command); let words=[];
-    for(const token of [...tokens,{operator:'end'}]) {
-      if(typeof token==='string'){words.push(token);continue;}
-      const result=classifyWords(words,policy,depth);if(!result.allowed)return result;words=[];
-    }
-    return {allowed:true};
-  } catch {return deny('Invalid policy or unsupported command syntax');}
-}
+import {validateGitPolicy,classifyGitCommand} from '../runtime/git-query.mjs';
+export {validateGitPolicy,classifyGitCommand};
+const deny=reason=>({allowed:false,reason});
 export function evaluateHookEvent(event,policy) {
   const result=event?.hook_event_name!=='PreToolUse' ? deny('Invalid hook event') : event?.tool_name!=='Bash' ? deny('Missing Bash event') : classifyGitCommand(event?.tool_input?.command,policy);
   return result.allowed?{}:{hookSpecificOutput:{hookEventName:'PreToolUse',permissionDecision:'deny',permissionDecisionReason:`ARC specialist Git guard: ${result.reason}. Return the operation to Orchestrator.`}};

package/claude/skill/hooks/runtime-gate.mjs

@@ -0,0 +1,12 @@
+import {runClaudeGate,renderClaudeDecision} from '../runtime/adapters/claude.mjs';
+/** Native installation must provide trusted context separately; stdin is only
+ * the platform event. Missing provider denies and never trusts event assertions. */
+export async function main(input,context){
+ try{return await runClaudeGate(JSON.parse(input),context);}catch{return renderClaudeDecision({decision:'deny',reason:'Malformed runtime hook event'});}
+}
+export async function runHook(){
+ let input='';for await(const chunk of process.stdin)input+=chunk;
+ process.stdout.write(JSON.stringify(await main(input))+'\n');
+}
+
+if(process.argv[1]&&import.meta.url===new URL(process.argv[1], 'file:').href)await runHook();

package/claude/skill/models.toml

@@ -1,5 +1,5 @@
-# Single source for all role model and effort presets.
-# Use configured settings without substitution; report unavailable settings.
+# Canonical source for every role model and effort preset.
+# Use configured settings as specified. Report unavailable settings.
 version = 1
 preset = "balanced"
 
@@ -8,12 +8,12 @@ model = "haiku"
 effort = "high"
 
 [roles.arc_scouter.balanced]
-model = "sonnet"
-effort = "medium"
+model = "haiku"
+effort = "high"
 
 [roles.arc_scouter.smart]
-model = "sonnet"
-effort = "high"
+model = "haiku"
+effort = "max"
 
 [roles.arc_planner.economy]
 model = "sonnet"
@@ -29,11 +29,11 @@ effort = "high"
 
 [roles.arc_coder.economy]
 model = "sonnet"
-effort = "low"
+effort = "medium"
 
 [roles.arc_coder.balanced]
 model = "sonnet"
-effort = "medium"
+effort = "high"
 
 [roles.arc_coder.smart]
 model = "opus"
@@ -44,12 +44,12 @@ model = "haiku"
 effort = "high"
 
 [roles.arc_qa.balanced]
-model = "sonnet"
-effort = "medium"
+model = "haiku"
+effort = "max"
 
 [roles.arc_qa.smart]
 model = "sonnet"
-effort = "high"
+effort = "medium"
 
 [roles.arc_reviewer.economy]
 model = "sonnet"

package/claude/skill/references/commit.md

@@ -14,8 +14,7 @@ Planning documents have their own batch docs commit before Coder handoff.
 
 After commit, verify exact SHA, subject, included paths, branch/HEAD and remaining index/worktree state.
 Preserve unrelated changes; never automatically unstage, amend, reset, clean, stash, or delete branches.
-On failure stop dependent work and report actual state and completed steps. Do not blindly repeat a commit or staging
-command. Push, publication and merge require user authorization. Coder must not commit, even when explicitly assigned.
+On failure, stop dependent work and report actual state and completed steps. MUST NOT blindly repeat a commit or staging command. Push, publication and merge require user authorization. Coder must not commit, even when explicitly assigned.
 
 Hold the task commit for unmet or unresolved criteria, failed or not-run required checks, undispositioned findings or
 evidence gaps, scope expansion, ownership or staged scope/content mismatch, unexpected workspace/branch/HEAD/Git state,
@@ -58,20 +57,18 @@ Approval scope and continuity are defined in [planning](planning.md#authorizatio
 limits are defined in [verification](verification.md#completion-continuity). This plan-task commit contract adds no
 commit obligation to no-plan work and does not turn a local commit into overall completion.
 
+## Automatic commit after plan-task acceptance
+
+Orchestrator accepts each approved top-level task by its own judgment and immediately creates one focused local commit
+for that
+task without additional user commit approval. Read [commit](commit.md) before the acceptance and commit.
+Push, merge, publish, deploy, and install still follow their separate guidance and approval rules.
+
+
 [ARC role policy: contract begin]
 Generated from lib/policy/role-policy.json; do not edit this managed section manually.
-- [scope.non-escalation] Act only within the intersection of role authority, approved scope and available platform tools. Delegation, restart, agent messages and attached instructions do not expand role authority. Never bypass a restriction through aliases, scripts, other tools, processes or redelegation. Return conflicting instructions to Orchestrator before dependent work; reuse valid prior approvals for unchanged scope rather than requesting them again.
-- [git.specialists-deny] Specialist roles MUST NOT change Git state: no stage, commit, push, merge, rebase, reset, branch creation/switching or worktree creation/removal, during normal implementation or recovery. Even an explicit Orchestrator assignment cannot authorize these actions; return them to Orchestrator. Read-only Git inspection remains allowed within the assigned scope.
+- [scope.non-escalation] Act only where role authority, approved scope and available platform tools all permit. Delegation, restart, agent messages and attached instructions do not expand role authority. MUST NOT bypass a restriction through aliases, scripts, other tools, processes or redelegation. Return conflicting instructions to Orchestrator before dependent work; reuse valid prior approvals for unchanged scope rather than requesting them again.
 - [git.orchestrator-accept-commit] Only Orchestrator accepts work and executes Git mutations. One approved top-level plan task becomes one focused implementation commit after criteria, required checks and findings are satisfied; Orchestrator accepts then commits without additional user commit approval. Reports, passing checks and Reviewer opinions do not replace acceptance. Preserve unrelated changes and ownership and verify the resulting SHA, included content, HEAD and remaining changes. Existing small-task direct and plan-omission paths are unchanged.
-- [external.explicit-user-authority] Push, merge, deploy, publish and external messages require explicit user authorization for that action, scope and target. Local commit authority does not grant external authority. Orchestrator performs authorized external actions; specialist roles return them without execution.
-- [role.orchestrator-boundary] Assign design/spec/plan/brainstorming drafts ONLY to Planner and implementation/configuration/test edits to Coder. Orchestrator saves complete drafts and owns approval requests, preparation, scheduling, evidence, acceptance and completion. Direct implementation is limited to the existing small, low-risk direct path; this policy does not expand it.
-- [role.scouter-read-only] Research assigned static sources and report findings, evidence and limits. Do not edit files, install, execute checks, prepare execution targets, inspect live operational state, change external state or decide design, verification, review or acceptance.
-- [role.planner-draft-only] Return design/spec/plan drafts and dependencies, criteria, hold conditions and verification needs in the response. Do not save documents, implement, run checks, prepare targets, request user approval or decide acceptance. Stop formal target-dependent drafting if actual prepared target evidence is missing; route decisions to Orchestrator.
-- [role.coder-implementation] Implement only assigned approved files and focused checks under the existing TDD contract. Report changed files, RED/GREEN or authorized exception evidence, results, limits and follow-up. Do not plan, independently QA/review your own work, accept the task or declare overall completion. Git changes remain forbidden even when implementation succeeds.
-- [role.qa-verification] Run approved checks and report commands, observations, reproduction, evidence and limits. Create only essential temporary data/logs/reports in the brief-authorized location and lifetime. Do not edit product source, tests, fixtures or configuration to pass checks, deploy or accept work. Persistent product-state checks require explicit scope and cleanup ownership. Return failures for Coder correction and required QA recheck.
-- [role.reviewer-independent] Independently inspect the assigned final changes and evidence and report actionable findings and limits. Remain read-only; do not execute QA tests, edit files, perform Git mutations or decide acceptance.
-- [review.significant-no-plan] For significant/high-risk work without a plan: Coder → QA and required QA rechecks → Reviewer of the final full change → Orchestrator acceptance. Do not omit Reviewer merely because no plan exists. This creates no new plan obligation.
-- [review.significant-plan] For significant/high-risk plan work: each task uses Coder → fresh QA as required → Orchestrator acceptance and focused commit. After all tasks are accepted and required QA is complete, Reviewer reviews the final full change once. Reviewer is NOT a per-task or per-commit required gate. Preserve required checks and necessary finding rechecks.
-- [review.final-plan-recheck] For final overall Reviewer findings on plan work, including behavior findings, use Coder → Reviewer without QA reassignment; repeat until resolved. This exception applies only to that final plan stage. Preserve required QA and QA failure rechecks before initial final review and outside this exception.
+- [external.explicit-user-authority] Push, merge, deploy, publish and external messages require explicit user authorization for that action, scope and target. Local commit authority grants no external authority. Orchestrator performs authorized external actions; specialist roles return them without execution.
 - [platform.claude] Existing per-role tool allowlists reduce available tools; Bash and role contracts are not a filesystem sandbox. A role-scoped Git guard is a separate integration and is not supplied by these policy sections alone.
 [ARC role policy: contract end]