cowork-flow 1.9.2 → 2.1.0

package/template/.cowork-flow/spec/contracts/decision-anchor.md

@@ -52,7 +52,7 @@ translated heading would simply stop being read.
 fact view (`services/fact_view.parse_decision_anchor`). Line-format conventions:
 
 - `## 验证命令`: one command per line (an optional `- ` prefix), truncated to 120
-  characters, at most 5 lines; the implementing agent runs them itself
+  characters, at most 10 lines; the implementing agent runs them itself
   (self-declared, self-checked) and the reviewer verifies the execution evidence.
 - `## 范围边界`: only the first non-empty line is taken, truncated to 160
   characters.
@@ -110,14 +110,14 @@ After merging (5 files): `decision-anchor.md` + `implement.jsonl` + `check.jsonl
   component.
   A **consequence** (expected cost, not a defect): **any byte change in
   `implement.jsonl`** (appending or removing a scope entry, rewording a `reason`,
-  a domain-guide entry auto-appended by `task context add`) **or a rewrite of a
+  a domain-guide entry) **or a rewrite of a
   referenced spec's prose invalidates an existing receipt**, requiring one more
   review run against the final state. Appending evidence, ticking ACs, and runtime
   metadata are not in that set.
 - **Light profile `meta.taskType: "tiny"`**: applies to `strict` tasks only
   (`legacy` + `tiny` stays a compatibility path). A light task **is still strict**
   — what it waives are three things: the review receipt, AC evidence, and
-  `dev_type`. It does **not** waive spec-check, the file-scope gate, or "AC rows
+  `dev_type`. It does **not** waive the file-scope gate or "AC rows
   are non-empty" (`LIFECYCLE-AC-003`/`004` still apply). Plan-file binding is not
   among the three, but the pre-existing field-level exemption for tiny applies, so
   a light task does not require `planFile` either. `tiny` **can only be declared at

package/template/.cowork-flow/spec/contracts/error-codes.md

@@ -44,6 +44,4 @@ to them:
 ## Exemptions
 
 `LIFECYCLE-AC-002` is the only code in this set a flag can waive
-(`--allow-missing-evidence`); spec-check's `--allow-unchecked` waives `unchecked`
-declarations, not a `LIFECYCLE-*` code. Details are in `evidence-completion.md` and
-`spec-checks.md`.
+(`--allow-missing-evidence`). Details are in `evidence-completion.md`.

package/template/.cowork-flow/spec/contracts/evidence-completion.md

@@ -40,7 +40,7 @@ direct lifecycle checks:
 | `LIFECYCLE-AC-001` | an unchecked AC row exists | none — do the work, or tick the completed rows |
 | `LIFECYCLE-AC-002` | a declared AC has no valid evidence record | `--allow-missing-evidence` (recorded in task.json `meta.evidenceExempt`, with `at`, `flag`, `by`, and the `missing` detail list) |
 | `LIFECYCLE-AC-003` | `gateProfile=strict` and decision-anchor yields no AC row | none — a strict task was already required to declare ACs at start, so reading none at completion has only three explanations: the anchor was rewritten, the task was created wrongly, or the anchor is undecodable (corrupted encoding) |
-| `LIFECYCLE-AC-004` | `gateProfile=strict` and the ac_evidence module cannot be imported | none — same family as `SPEC-CHECK-EXECUTOR-ERROR`: a broken module is not "nothing to check"; the message carries the original exception, and you rerun once the runtime install is fixed |
+| `LIFECYCLE-AC-004` | `gateProfile=strict` and the ac_evidence module cannot be imported | none — a broken module is not "nothing to check"; the message carries the original exception, and you rerun once the runtime install is fixed |
 
 - The first two codes can appear together; `--allow-missing-evidence` waives
   `LIFECYCLE-AC-002` only, never `003`/`004`.
@@ -51,8 +51,8 @@ direct lifecycle checks:
 - **Strict path**: a `gateProfile=strict` task re-verifies AC existence and
   evidence-module availability at completion — the start-time AC declaration
   requirement does not lapse because completion cannot read it.
-- The `meta.evidenceExempt` trace has the same shape as spec-check's
-  `specCheckExempt`: retries do not accumulate, the latest completion result wins.
+- The `meta.evidenceExempt` trace does not accumulate: retries leave only the
+  latest completion result.
 - **An exemption record must name which items were waived and who approved it**:
   `meta.evidenceExempt` = `{"at", "flag": "--allow-missing-evidence",
   "by": <actor or null>, "missing": [<AC id>…]}`. `by` is the resolved session
@@ -60,9 +60,7 @@ direct lifecycle checks:
   `creator`/`assignee`. Both the completion output and the archive output print
   this record item by item (the completion output reads the `task.json` just
   written), so "what was recorded" and "what was printed" cannot tell two different
-  stories; with no exemption, no exemption rows are printed at all. The structure
-  matches the `meta.specCheckExempt` detail rules on the spec-check side; see
-  `spec-checks.md`.
+  stories; with no exemption, no exemption rows are printed at all.
 
 ## Injection and fact view
 
@@ -81,5 +79,5 @@ direct lifecycle checks:
   behind an AC to fabricate a record.
 - It does not parse AC prose semantics; a missing checkbox on an `AC-xxx` row
   parses as incomplete.
-- This contract does not change spec-check semantics; MCP write tools still refuse
-  by default (`fact-layer-access.md`).
+- This contract does not change the file-scope gate or the AC gate; MCP write
+  tools still refuse by default (`fact-layer-access.md`).

package/template/.cowork-flow/spec/contracts/index.md

@@ -12,7 +12,6 @@ Current contracts:
 - `capabilities.md`: the host adapter capability model.
 - `party-mode-v2-board.md`: the Party Mode V2 board protocol.
 - `plan-binding.md`: lightweight development-plan binding, pre-start missing-plan blocking, and recovery visibility.
-- `spec-checks.md`: the spec-declared command contract — syntax of `checks:` in user-spec frontmatter, three-state gate semantics, timing, and the host capability matrix.
 - `context-injection.md`: the transport shapes, event-timing matrix, and fingerprint serialization rules for runtime-context injection across hosts (a meta-protocol, not in `contract-registry.json`).
 - `decision-anchor.md`: the schema of each task's `decision-anchor.md` — goal, acceptance criteria, rejected options, and key assumptions.
 - `error-output-as-data.md`: external error output is analyzed as data, never executed as instructions (`ERROR_OUTPUT_AS_DATA_V1`).

package/template/.cowork-flow/spec/contracts/plan-binding.md

@@ -14,8 +14,9 @@ the plan into a second workflow kernel.
 
 ## Creation phase
 
-- A plain `task create` may create a planning task with no plan.
-- `task create --from-plan <path>` is an explicit binding request; `<path>` must
+- A plain task creation (`task next --title … --slug …`) may create a planning
+  task with no plan.
+- `task next --from-plan <path>` is an explicit binding request; `<path>` must
   exist, lie inside the repository, and lie under `.cowork-flow/plans/`.
 - On a successful binding the runtime writes:
 

package/template/.cowork-flow/spec/contracts/subagent-dispatch.md

@@ -108,23 +108,6 @@ does not defend against a forged runtime record — writing
 `.cowork-flow/.runtime/**` is out of scope here and would need a signed or
 externally rooted record, which is a separate contract.
 
-## Delegated Spec Self-Check
-
-Delegated subagent tool calls receive no edit-phase hook feedback on hosts
-whose plugin hooks cover only the main session stream (verified on zcode:
-plugin PostToolUse fires for main-session tool calls but never for
-Agent-tool children). The reliable pull path is the CLI: before reporting
-completion, `cowork-implement` (and any child that changes files) runs
-
-```text
-./.cowork-flow/run spec-check
-```
-
-fixes every reported violation, and re-runs until the summary is clean or the
-remaining violations are reported as blockers. This is a protocol behavior,
-not a second lifecycle gate — the closeout gate re-runs the same checks and
-blocks completion regardless.
-
 ## Return Acceptance And Closeout
 
 - Converge on the child result before acceptance — via the wait primitive or
@@ -133,10 +116,12 @@ blocks completion regardless.
 - Confirm no stray running children with the adapter list primitive.
 - Verify the child report by checking files, commands, and results; do not
   trust completed text alone.
-- Before accepting delegated output, run `./.cowork-flow/run spec-check` in
-  the main session and treat every violation as an acceptance blocker: the
-  child receives no edit-phase hook feedback, so acceptance-time checking is
-  the earliest reliable checkpoint for delegated work.
+- Before accepting delegated output, verify the child's changed paths against
+  the task scope and the applicable `spec/` requirements from the diff
+  (`git diff --stat` / `task next <dir> --validate`): child sessions receive no
+  edit-phase hook feedback on hosts whose plugin hooks cover only the main
+  session stream, so acceptance-time review is the earliest reliable checkpoint
+  for delegated work.
 - After completion or failure, close the child with the adapter cancel/close
   primitive and clean the runtime context sessions.
 - The child remains a leaf executor and must not dispatch, wait for, list, or

package/template/.cowork-flow/spec/contracts/task-adopt.md

@@ -74,7 +74,7 @@ that does not advance status); `check_result` is `null` (no check is exempted).
 ## Session binding
 
 On successful adoption the CLI binds the adopter's session to that task (the same
-shape as a rebind by `task next <dir>` or the binding after `task create`), so a
+shape as a rebind by `task next <dir>` or the binding at task creation), so a
 later `task next <dir> --run` can omit the directory and continue the
 review/complete/archive chain.
 

package/template/.cowork-flow/spec/runtime/contract-registry.json

@@ -115,19 +115,6 @@
         "when changing task start readiness",
         "when changing resume context for active tasks"
       ]
-    },
-    {
-      "id": "SPEC_CHECKS_V1",
-      "path": ".cowork-flow/spec/contracts/spec-checks.md",
-      "digest": [
-        "Specs may declare `checks:` commands in frontmatter; the mechanism runs declarations, never prose.",
-        "A declared command that cannot be found counts as unchecked and blocks completion."
-      ],
-      "readWhen": [
-        "before adding or editing spec files",
-        "when a spec clause can be judged by a command exit code",
-        "when spec-check reports violations or unchecked"
-      ]
     }
   ],
   "references": [

package/template/.cowork-flow/spec/runtime/host-assets.json

@@ -155,7 +155,7 @@
         "runtimeContextDispatch": "native",
         "runtimeContextBinding": "shim",
         "runtimeContextCleanup": "native",
-        "editScopeWarning": "unsupported"
+        "editScopeWarning": "plugin"
       },
       "commandTargets": [
         {
@@ -204,7 +204,7 @@
         "runtimeContextDispatch": "native",
         "runtimeContextBinding": "shim",
         "runtimeContextCleanup": "native",
-        "editScopeWarning": "unsupported"
+        "editScopeWarning": "plugin"
       },
       "commandTargets": [],
       "payload": {
@@ -251,7 +251,7 @@
         "runtimeContextDispatch": "native",
         "runtimeContextBinding": "shim",
         "runtimeContextCleanup": "native",
-        "editScopeWarning": "unsupported"
+        "editScopeWarning": "plugin"
       },
       "commandTargets": [
         {
@@ -300,7 +300,7 @@
         "runtimeContextDispatch": "native",
         "runtimeContextBinding": "shim",
         "runtimeContextCleanup": "shim",
-        "editScopeWarning": "unsupported"
+        "editScopeWarning": "plugin"
       },
       "commandTargets": [],
       "payload": null
@@ -431,7 +431,7 @@
         "runtimeContextDispatch": "native",
         "runtimeContextBinding": "shim",
         "runtimeContextCleanup": "native",
-        "editScopeWarning": "unsupported"
+        "editScopeWarning": "plugin"
       },
       "commandTargets": [],
       "payload": {
@@ -460,8 +460,8 @@
       ".cowork-flow/.version",
       ".cowork-flow/run",
       ".cowork-flow/run.cmd",
-      ".cowork-flow/spec/contracts/spec-checks.md",
-      ".cowork-flow/spec/contracts/workflow-state-templates.md"
+      ".cowork-flow/spec/contracts/workflow-state-templates.md",
+      ".cowork-flow/spec/runtime/scope-rules.json"
     ],
     "safePrefixes": [
       ".cowork-flow/"
@@ -515,6 +515,7 @@
       ".cowork-flow/scripts/application",
       ".cowork-flow/scripts/services/batch_execution.py",
       ".cowork-flow/scripts/services/decision_review.py",
+      ".cowork-flow/scripts/services/spec_check.py",
       ".cowork-flow/scripts/commands",
       ".cowork-flow/scripts/common",
       ".cowork-flow/scripts/common/__init__.py",
@@ -567,6 +568,7 @@
       ".cowork-flow/scripts/subagent.py",
       ".cowork-flow/scripts/task.py",
       ".cowork-flow/spec/contracts/entry-contract.md",
+      ".cowork-flow/spec/contracts/spec-checks.md",
       ".cowork-flow/spec/runtime/rules.json",
       ".cowork-flow/spec/schemas/rules.schema.json",
       ".cowork-flow/spec/runtime/skill-registry.json",
@@ -575,6 +577,7 @@
       ".cowork-flow/scripts/adapters/cli/add_session.py",
       ".cowork-flow/workspace/index.md",
       ".cowork-flow/scripts/adapters/cli/change.py",
+      ".cowork-flow/scripts/adapters/cli/spec_check.py",
       ".cowork-flow/changes/",
       ".cowork-flow/skills/adversarial-review",
       ".cowork-flow/skills/agent-dispatch",

package/template/.cowork-flow/spec/runtime/scope-rules.json

@@ -8,9 +8,9 @@
     "trailingSlashRejectedTypes": ["planned-file", "deleted-file"]
   },
   "stageContract": {
-    "budget": 1200,
+    "budget": 3400,
     "scopeLimit": 8,
     "specLimit": 4,
-    "verifyLimit": 3
+    "verifyLimit": 10
   }
 }

package/template/.kimi-code/agents/cowork-check.md

@@ -24,6 +24,6 @@ Execution:
 Rules:
 
 - Do not invoke subagents.
-- Do not run task start, finish, archive, unscoped resume, commit, or push.
+- Do not run task lifecycle transitions, unscoped resume, commit, or push.
 - Treat backend/frontend natural-language specs as checklist context, not dynamic hard validators.
 - Do not accept shallow tests that would still pass when target behavior breaks.

package/template/.kimi-code/agents/cowork-implement.md

@@ -25,6 +25,6 @@ Execution:
 Rules:
 
 - Do not invoke subagents.
-- Do not run task start, finish, archive, unscoped resume, commit, or push.
+- Do not run task lifecycle transitions, unscoped resume, commit, or push.
 - Do not create task-local review artifacts, `tdd.jsonl`, or TDD evidence records in `check.jsonl`.
 - Do not claim completion without current verification.

package/template/.kimi-code/agents/cowork-research.md

@@ -20,4 +20,4 @@ Rules:
 
 - Do not invoke subagents.
 - Do not edit code, specs, task state, or git state.
-- Do not run task start, finish, archive, unscoped resume, commit, or push.
+- Do not run task lifecycle transitions, unscoped resume, commit, or push.

package/template/.opencode/agents/cowork-check.md

@@ -28,6 +28,6 @@ Execution:
 Rules:
 
 - Do not use the `task` tool or invoke subagents.
-- Do not run task start, finish, archive, unscoped resume, commit, or push.
+- Do not run task lifecycle transitions, unscoped resume, commit, or push.
 - Treat backend/frontend natural-language specs as checklist context, not dynamic hard validators.
 - Do not accept shallow tests that would still pass when target behavior breaks.

package/template/.opencode/agents/cowork-implement.md

@@ -29,6 +29,6 @@ Execution:
 Rules:
 
 - Do not use the `task` tool or invoke subagents.
-- Do not run task start, finish, archive, unscoped resume, commit, or push.
+- Do not run task lifecycle transitions, unscoped resume, commit, or push.
 - Do not create task-local review artifacts, `tdd.jsonl`, or TDD evidence records in `check.jsonl`.
 - Do not claim completion without current verification.

package/template/.opencode/agents/cowork-research.md

@@ -26,4 +26,4 @@ Rules:
 
 - Do not use the `task` tool or invoke subagents.
 - Do not edit code, specs, task state, or git state.
-- Do not run task start, finish, archive, unscoped resume, commit, or push.
+- Do not run task lifecycle transitions, unscoped resume, commit, or push.

package/template/.opencode/cowork-flow/plugin-core.js

@@ -1,11 +1,11 @@
 // Transport shim behind the opencode plugin. Every workflow fact
 // (contract digest, workflow-state, decision anchor, stage contract,
-// runtime-context bind) is rendered by the Python source
-// <scripts>/adapters/host/inject.py --host opencode; this module moves
-// bytes only. What stays here is what the Python side cannot reach:
-// the config-hook skills registration, the shell.env context-key
-// export, and the edit-phase spec-check the tool.execute.after hook
-// delegates to the project runtime.
+// runtime-context bind, edit-scope warning) is rendered by the Python
+// source <scripts>/adapters/host/inject.py --host opencode; this module
+// moves bytes only. What stays here is what the Python side cannot
+// reach: the config-hook skills registration, the shell.env context-key
+// export, and the tool-shape translation for the tool.execute.after
+// edit-scope delegation.
 //
 // This module must NOT live under plugins/: opencode
 // treats every file directly inside plugins/ as a plugin
@@ -16,7 +16,7 @@
 // install, so the adapter's relative import resolves in
 // both.
 
-import { spawn } from "node:child_process"
+import { spawn, spawnSync } from "node:child_process"
 import { existsSync } from "node:fs"
 import { dirname, resolve } from "node:path"
 import { fileURLToPath } from "node:url"
@@ -24,6 +24,27 @@ import { fileURLToPath } from "node:url"
 const DIR_WORKFLOW = ".cowork-flow"
 // One prompt assembly must not wait longer than a host hook event.
 const INJECT_TIMEOUT_MS = 4800
+// The .cowork-flow/run floor, reused here: a candidate that cannot run
+// Python 3.10+ is skipped like a missing binary, so a stale `python3`
+// never hides a working `python` further down the list.
+const MIN_PYTHON_CHECK =
+  "import sys; raise SystemExit(0 if sys.version_info >= (3, 10) else 1)"
+
+function interpreterIsUsable(candidate) {
+  try {
+    const probe = spawnSync(candidate[0], [...candidate.slice(1), "-c", MIN_PYTHON_CHECK], {
+      timeout: INJECT_TIMEOUT_MS,
+      windowsHide: true,
+    })
+    // A probe killed by its own timeout reached no verdict — a loaded machine,
+    // not a bad interpreter — so let the real spawn decide; it carries the
+    // same timeout and its own diagnostics.
+    if (probe.error && probe.error.code === "ETIMEDOUT") return true
+    return !probe.error && probe.status === 0
+  } catch {
+    return false
+  }
+}
 
 // Last-resort repository root: this module lives at
 // <payload>/cowork-flow/plugin-core.js, next to plugins/,
@@ -175,8 +196,9 @@ function runInject(candidate, script, payload) {
 // inject.py and hand back whatever it printed. The payload spreads the
 // host input so every session/runtime-context key the Python identity
 // table knows arrives unchanged; hook_event_name and cwd are the two
-// fields the hook contract requires.
-async function renderViaInject(input) {
+// fields the hook contract requires. `overrides` swaps the event name
+// and adds the tool fields the PostToolUse contract needs.
+async function renderViaInject(input, overrides = null) {
   if (
     process.env.COWORK_FLOW_HOOKS === "0" ||
     process.env.COWORK_FLOW_DISABLE_HOOKS === "1"
@@ -188,21 +210,57 @@ async function renderViaInject(input) {
   if (!script) {
     return ""
   }
+  const extra = overrides && typeof overrides === "object" ? overrides : {}
   const payload = {
     ...(input && typeof input === "object" ? input : {}),
-    hook_event_name: "UserPromptSubmit",
+    ...extra,
+    hook_event_name: extra.hook_event_name || "UserPromptSubmit",
     cwd: inputCwd(input) || (root === pluginRoot ? null : root) || process.cwd(),
   }
   for (const candidate of pythonCandidates()) {
+    if (!interpreterIsUsable(candidate)) {
+      continue
+    }
     const result = await runInject(candidate, script, payload)
     if (!result.ran) {
       continue
     }
     return result.stdout.trim()
   }
+  console.error(
+    "cowork-flow opencode plugin: no Python 3.10+ interpreter found; skipping injection"
+  )
   return ""
 }
 
+// Editor-phase scope warning: opencode sessions get the same
+// single-line out-of-scope advisory the other hosts receive on
+// PostToolUse. Best-effort — a missing runtime, a timeout, or any
+// error stays silent and never blocks the edit that already happened.
+const EDIT_TOOL_NAMES = new Set(["edit", "write"])
+
+function editedFilePath(input) {
+  const tool = typeof input?.tool === "string" ? input.tool : ""
+  if (!EDIT_TOOL_NAMES.has(tool)) {
+    return ""
+  }
+  const args = input?.args
+  const candidate = args && typeof args === "object" ? args.filePath : null
+  return typeof candidate === "string" && candidate.trim() ? candidate.trim() : ""
+}
+
+async function renderEditScopeWarning(input) {
+  const filePath = editedFilePath(input)
+  if (!filePath) {
+    return ""
+  }
+  return renderViaInject(input, {
+    hook_event_name: "PostToolUse",
+    tool_name: typeof input?.tool === "string" ? input.tool : "edit",
+    tool_input: { file_path: filePath },
+  })
+}
+
 function sanitize(value) {
   return String(value ?? "")
     .trim()
@@ -262,82 +320,6 @@ function injectShellEnv(input, output) {
   }
 }
 
-// Editor-phase spec-check: opencode sessions get the same
-// single-line violation hint zcode and claude-code
-// receive. Best-effort — a missing runtime, a timeout, or
-// any error stays silent and never blocks the edit that
-// already happened.
-const EDIT_TOOL_NAMES = new Set(["edit", "write"])
-const EDIT_CHECK_TIMEOUT_MS = 2500
-
-function editedFilePath(input) {
-  const tool = typeof input?.tool === "string" ? input.tool : ""
-  if (!EDIT_TOOL_NAMES.has(tool)) {
-    return ""
-  }
-  const args = input?.args
-  const candidate = args && typeof args === "object" ? args.filePath : null
-  return typeof candidate === "string" && candidate.trim() ? candidate.trim() : ""
-}
-
-function runEditSpecCheck(root, filePath) {
-  return new Promise((resolvePromise) => {
-    let settled = false
-    const finish = (value) => {
-      if (!settled) {
-        settled = true
-        resolvePromise(value)
-      }
-    }
-    const entry = resolve(
-      root,
-      DIR_WORKFLOW,
-      process.platform === "win32" ? "run.cmd" : "run"
-    )
-    if (!existsSync(entry)) {
-      finish("")
-      return
-    }
-    let child
-    try {
-      child = spawn(
-        entry,
-        ["spec-check", "--phase", "edit", "--file", filePath, "--throttled"],
-        {
-          cwd: root,
-          stdio: ["ignore", "pipe", "ignore"],
-          shell: process.platform === "win32",
-        }
-      )
-    } catch {
-      finish("")
-      return
-    }
-    const timer = setTimeout(() => {
-      try {
-        child.kill()
-      } catch {
-        // the edit must not be held up by a stuck checker
-      }
-      finish("")
-    }, EDIT_CHECK_TIMEOUT_MS)
-    let stdout = ""
-    if (child.stdout) {
-      child.stdout.on("data", (chunk) => {
-        stdout += String(chunk)
-      })
-    }
-    child.on("error", () => {
-      clearTimeout(timer)
-      finish("")
-    })
-    child.on("close", () => {
-      clearTimeout(timer)
-      finish(stdout.trim())
-    })
-  })
-}
-
 // The payload's own skills directory, located from this
 // module's file path and not from the repository root: the
 // machine install puts this file in
@@ -382,11 +364,11 @@ export function registerPayloadSkills(config) {
 
 // The plugin adapter imports the hook helpers; these are
 // the unit-test surface (transport, fail-open, shell env,
-// edit-phase delegation). opencode never reads this module.
+// edit-scope delegation). opencode never reads this module.
 export {
   renderViaInject,
   editedFilePath,
+  renderEditScopeWarning,
   findRepoRoot,
   injectShellEnv,
-  runEditSpecCheck,
 }

package/template/.opencode/plugins/cowork-flow.js

@@ -7,12 +7,10 @@
 // re-exported helper would be called as a plugin and break
 // host bootstrap.
 import {
-  editedFilePath,
-  findRepoRoot,
   injectShellEnv,
   registerPayloadSkills,
-  renderViaInject,
-  runEditSpecCheck
+  renderEditScopeWarning,
+  renderViaInject
 } from "../cowork-flow/plugin-core.js"
 
 export const CoworkFlowPlugin = async () => {
@@ -37,12 +35,12 @@ export const CoworkFlowPlugin = async () => {
         output.system.push(text)
       }
     },
+    // Editor-phase scope advisory: the tool already ran, so
+    // the single out-of-scope line is appended to its output
+    // and the call is never blocked. Non-edit tools and a
+    // missing/failing runtime stay silent.
     "tool.execute.after": async (input, output) => {
-      const filePath = editedFilePath(input)
-      if (!filePath) {
-        return
-      }
-      const warning = await runEditSpecCheck(findRepoRoot(input), filePath)
+      const warning = await renderEditScopeWarning(input)
       if (warning) {
         output.output = [output.output, warning].filter(Boolean).join("\n")
       }

package/template/AGENTS.md

@@ -144,5 +144,4 @@
 
 <!-- COWORK-FLOW:START -->
 项目流程以 `task next`、runtime gate、Skill command manifests 和 `.cowork-flow/spec/` 硬契约为准；不要维护第二套流程文档或 Skill 注册控制面。
-规范声明的检查以 `.cowork-flow/spec/contracts/spec-checks.md` 为准；交付或收口前运行 `./.cowork-flow/run spec-check`。
 <!-- COWORK-FLOW:END -->

package/template/skills/agent-dispatch/SKILL.md

@@ -30,21 +30,6 @@ Use this Skill only inside fixed subagents such as `cowork-implement`,
 - Treat runtime gates as CLI adapters backed by kernel services; this Skill may
   explain when to run or report them, but does not enforce them.
 
-## Spec Self-Check
-
-Delegated subagent tool calls receive no edit-phase hook feedback on hosts
-whose plugin hooks cover only the main session stream — a `spec-check[...]
-violation` line never reaches this session, even when the edit violates a
-declared check. Before reporting completion after any file change, run:
-
-```text
-./.cowork-flow/run spec-check
-```
-
-Fix every reported violation and re-run until the summary is clean, or report
-the remaining violations as blockers. Honor any hook feedback the host does
-deliver; the self-check exists because delivery is not guaranteed.
-
 ## Role Outputs
 
 - `cowork-implement`: report changed files, acceptance IDs, verification