@c4a/context-cli 0.6.1 → 0.6.3

package/plugins/claude/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "context",
   "description": "Maintain a project-local knowledge workspace through init and next-step agent guidance.",
-  "version": "0.6.1",
+  "version": "0.6.3",
   "author": {
     "name": "c4a"
   },

package/plugins/claude/commands/continue.md

@@ -6,27 +6,78 @@ allowed-tools: Bash(context:*), Bash(bun:*), Bash(cd *)
 
 ## Your Task
 
-Use this as the conversational entry for an existing Context workspace. There is
-no `context continue` CLI primitive; the command runs lower-level `context ...`
-commands only when the workspace state requires them.
+Use this as the conversational entry for an existing Context workspace. There
+is no `context continue` CLI primitive. Without explicit fully managed
+authority, start with:
+
+```bash
+context status --format json
+```
+
+If the user explicitly asks to enable debugging, first run
+`context debug enable`. It sets `package.json` `context.debug=true` and records
+subsequent CLI and Agent Graph events only below `.tmp/context-runtime/debug/`.
+Do not enable it proactively; tracing is not workflow authority or evidence.
+
+When the user explicitly requests fully managed operation in this conversation,
+start with the managed loop instead of a manual status/action cycle:
+
+```bash
+context run --managed --until blocked-or-complete --format json
+```
+
+Never persist or reuse that authority in another conversation. While the
+request remains active, use `--managed` for every resumed status evaluation;
+stop using it when the conversation ends or the user revokes it.
 
 If the user is starting a new workspace or a new batch from a raw repository
 root, do not run `context status` first. Use the public Context init entry or
 `context init` to create the workspace, complete the init setup command, then
 return here from the initialized workspace.
 
-If `context status` reports `workspace-not-found` and points at a configured
-`context.workspaceDir`, do not keep working from the host repository root. Enter
-that workspace when it exists, or initialize it through the init workflow after
-confirming with the user.
+The managed loop is the default entry for an explicitly managed conversation,
+not an optional optimization. Pass an additional `--authority` only when the user explicitly granted that
+non-managed authority in this conversation. This loop executes only one
+revision-bound command at a time and re-evaluates after every receipt. It stops
+before read-only interpretation, project configuration, unresolved authority,
+diagnostics, or a non-unique command plan. On stop, resume from the returned
+`workflow.current`; do not derive a command from earlier steps.
 
 Language policy: explain, ask, confirm, and summarize in the user's current
 conversation language. Keep CLI commands, flags, paths, ids, status enum values,
 JSONL payload keys, `source_ref` values, and copied CLI output tokens unchanged.
 
-Use the internal `context:skill-continue-workflow` procedure end to end. It owns the
-status loop, safe mechanical next steps, source/scope gate, review gate, package
-gate, and final report rules.
+Treat `workflow.current` as the current-step authority:
+
+1. Read every `resources.required` item whose `read_state` is
+   `read-required`. Read a `path` directly; for a resource with `command`,
+   execute that command and read the returned file. Keep read receipts only in
+   the current conversation and pass the merged receipt set back with
+   `context status --resource-receipts @<file>`; an unchanged static digest or
+   matching dynamic Route revision then returns `read_state: current`.
+   Materializing a resource is not a read: use the returned
+   `after_read_receipts` only after reading the complete returned file. A
+   `context.source-body/*` resource is the complete captured Markdown body;
+   source indexes and heading metadata never replace it. The exact
+   `resources.after_read.command` returns the re-evaluated `workflow.current`;
+   continue from that response without an additional status call.
+2. At a Gate, keep conditional context phase-local. An `inspection_action`
+   Skill or Schema is read only when performing that pre-decision inspection;
+   a `resolution_action` Skill or Schema is read only after the user confirms
+   the Gate. Neither replaces ordinary `resources.required`.
+3. Execute only `commands` returned by the Route, preserving revision and
+   authority flags exactly. A command marked `after-human-confirmation` must
+   wait for the current Gate decision. Run a command whose
+   `execution.target` is `agent-host` as a top-level host action with the
+   host's external and credential access, not inside a restricted child
+   sandbox. Request host approval when required; never weaken credential
+   storage as a workaround.
+4. If `configuration` is present, edit only the named project file using the
+   selected resources as its contract.
+5. After every action or configuration change, run status again. The managed
+   `--until` loop performs this re-evaluation internally. A phase-local
+   `next_action` can continue that operation but never replaces the workspace
+   Route.
 
 Do not infer repo sources, extraction scope, review decisions, or package output
 choices from surrounding files. Do not call source-repo operations such as

package/plugins/claude/commands/init.md

@@ -1,21 +1,36 @@
 ---
 description: "Initialize a Context knowledge workspace."
-argument-hint: "[project-dir] [--name <name>]"
+argument-hint: "[project-dir] [--name <name>] [--language en|zh-CN] [--debug]"
 allowed-tools: Bash(context:*), Bash(bun:*), Bash(cd *)
 ---
 
 ## Your Task
 
-Initialize a Context workspace with the global CLI, then continue only through
-safe mechanical setup steps until the first human decision gate.
+Initialize a Context workspace with the global CLI, complete the returned setup
+step, then hand control to the current workflow route.
 
-Language policy: explain, ask, confirm, and summarize in the user's current
-conversation language. Keep CLI commands, flags, file paths, package names,
-enum values, payload keys, and copied CLI output tokens unchanged.
+Use the user's language for conversation. Keep command and payload tokens
+unchanged.
 
-Use the internal `context:skill-init-workspace` procedure end to end. It owns
-the `context init` invocation, dependency install follow-up, generated
-`AGENTS.md` handoff, status handoff, and stop conditions.
+Run `context init [project-dir] [--name <name>] --language <language>`. Use the
+user's explicit language choice when present; otherwise pass `zh-CN` for a
+Chinese conversation and `en` for an English conversation. This explicit CLI
+value controls generated workspace instructions and starter templates. Never
+substitute `.` when `project-dir` was omitted; the default is `context/`. Use
+`--dev` only for an explicitly requested local-link test.
+Add `--debug` only when the user explicitly asks to trace this workspace. Debug
+mode is otherwise off by default.
 
-Do not add extra project-local agent setup. Do not infer repo sources or
-extraction scope from the surrounding monorepo after setup.
+If init reports `init-target-nonempty`, explain that existing files would share
+the workspace root. Run the returned `--allow-nonempty` command only after
+explicit confirmation.
+
+Execute the returned setup command, enter the project root, and read its
+generated `AGENTS.md`. Then run `context status --format json`, adding
+`--managed` only for fully managed operation explicitly authorized in this
+conversation. Treat `workflow.current` as authoritative: read its required
+resources, execute only exact commands, honor unresolved human gates, and
+reevaluate status after each action.
+
+Do not add extra project-local agent setup or infer sources from the surrounding
+monorepo.

package/plugins/codex/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "context",
-  "version": "0.6.1",
+  "version": "0.6.3",
   "description": "Maintain a project-local knowledge workspace through init and next-step agent guidance.",
   "author": {
     "name": "c4a"
@@ -18,7 +18,7 @@
   "skills": "./skills/",
   "interface": {
     "displayName": "C4A Context",
-    "shortDescription": "Initialize and advance a local, source-linked project knowledge workspace.\nv0.6.1",
+    "shortDescription": "Initialize and advance a local, source-linked project knowledge workspace.\nv0.6.3",
     "longDescription": "Create a Context workspace and use agent-guided next steps to register sources, run extraction, review candidates, build package outputs, and verify health without silently mutating source repositories.",
     "developerName": "c4a",
     "category": "Productivity",

package/plugins/codex/skills/continue/SKILL.md

@@ -13,33 +13,83 @@ Public Context entry for agents that expose skills instead of slash commands.
 - Public entry: `continue`
 - Host command names are installation-specific; use the command or skill surfaced by the current host instead of deriving a filesystem path from an example name.
 - CLI primitive prefix: `context ...`
-- Internal procedures live under `references/internal-procedures/`; read each referenced file in full before following that step.
 
 ---
 
 ## Workflow
 
-Use this as the conversational entry for an existing Context workspace. There is
-no `context continue` CLI primitive; the command runs lower-level `context ...`
-commands only when the workspace state requires them.
+Use this as the conversational entry for an existing Context workspace. There
+is no `context continue` CLI primitive. Without explicit fully managed
+authority, start with:
+
+```bash
+context status --format json
+```
+
+If the user explicitly asks to enable debugging, first run
+`context debug enable`. It sets `package.json` `context.debug=true` and records
+subsequent CLI and Agent Graph events only below `.tmp/context-runtime/debug/`.
+Do not enable it proactively; tracing is not workflow authority or evidence.
+
+When the user explicitly requests fully managed operation in this conversation,
+start with the managed loop instead of a manual status/action cycle:
+
+```bash
+context run --managed --until blocked-or-complete --format json
+```
+
+Never persist or reuse that authority in another conversation. While the
+request remains active, use `--managed` for every resumed status evaluation;
+stop using it when the conversation ends or the user revokes it.
 
 If the user is starting a new workspace or a new batch from a raw repository
 root, do not run `context status` first. Use the public Context init entry or
 `context init` to create the workspace, complete the init setup command, then
 return here from the initialized workspace.
 
-If `context status` reports `workspace-not-found` and points at a configured
-`context.workspaceDir`, do not keep working from the host repository root. Enter
-that workspace when it exists, or initialize it through the init workflow after
-confirming with the user.
+The managed loop is the default entry for an explicitly managed conversation,
+not an optional optimization. Pass an additional `--authority` only when the user explicitly granted that
+non-managed authority in this conversation. This loop executes only one
+revision-bound command at a time and re-evaluates after every receipt. It stops
+before read-only interpretation, project configuration, unresolved authority,
+diagnostics, or a non-unique command plan. On stop, resume from the returned
+`workflow.current`; do not derive a command from earlier steps.
 
 Language policy: explain, ask, confirm, and summarize in the user's current
 conversation language. Keep CLI commands, flags, paths, ids, status enum values,
 JSONL payload keys, `source_ref` values, and copied CLI output tokens unchanged.
 
-Use the procedure in `references/internal-procedures/skill-continue-workflow.md` end to end. It owns the
-status loop, safe mechanical next steps, source/scope gate, review gate, package
-gate, and final report rules.
+Treat `workflow.current` as the current-step authority:
+
+1. Read every `resources.required` item whose `read_state` is
+   `read-required`. Read a `path` directly; for a resource with `command`,
+   execute that command and read the returned file. Keep read receipts only in
+   the current conversation and pass the merged receipt set back with
+   `context status --resource-receipts @<file>`; an unchanged static digest or
+   matching dynamic Route revision then returns `read_state: current`.
+   Materializing a resource is not a read: use the returned
+   `after_read_receipts` only after reading the complete returned file. A
+   `context.source-body/*` resource is the complete captured Markdown body;
+   source indexes and heading metadata never replace it. The exact
+   `resources.after_read.command` returns the re-evaluated `workflow.current`;
+   continue from that response without an additional status call.
+2. At a Gate, keep conditional context phase-local. An `inspection_action`
+   Skill or Schema is read only when performing that pre-decision inspection;
+   a `resolution_action` Skill or Schema is read only after the user confirms
+   the Gate. Neither replaces ordinary `resources.required`.
+3. Execute only `commands` returned by the Route, preserving revision and
+   authority flags exactly. A command marked `after-human-confirmation` must
+   wait for the current Gate decision. Run a command whose
+   `execution.target` is `agent-host` as a top-level host action with the
+   host's external and credential access, not inside a restricted child
+   sandbox. Request host approval when required; never weaken credential
+   storage as a workaround.
+4. If `configuration` is present, edit only the named project file using the
+   selected resources as its contract.
+5. After every action or configuration change, run status again. The managed
+   `--until` loop performs this re-evaluation internally. A phase-local
+   `next_action` can continue that operation but never replaces the workspace
+   Route.
 
 Do not infer repo sources, extraction scope, review decisions, or package output
 choices from surrounding files. Do not call source-repo operations such as

package/plugins/codex/skills/init/SKILL.md

@@ -13,22 +13,36 @@ Public Context entry for agents that expose skills instead of slash commands.
 - Public entry: `init`
 - Host command names are installation-specific; use the command or skill surfaced by the current host instead of deriving a filesystem path from an example name.
 - CLI primitive prefix: `context ...`
-- Internal procedures live under `references/internal-procedures/`; read each referenced file in full before following that step.
 
 ---
 
 ## Workflow
 
-Initialize a Context workspace with the global CLI, then continue only through
-safe mechanical setup steps until the first human decision gate.
-
-Language policy: explain, ask, confirm, and summarize in the user's current
-conversation language. Keep CLI commands, flags, file paths, package names,
-enum values, payload keys, and copied CLI output tokens unchanged.
-
-Use the procedure in `references/internal-procedures/skill-init-workspace.md` end to end. It owns
-the `context init` invocation, dependency install follow-up, generated
-`AGENTS.md` handoff, status handoff, and stop conditions.
-
-Do not add extra project-local agent setup. Do not infer repo sources or
-extraction scope from the surrounding monorepo after setup.
+Initialize a Context workspace with the global CLI, complete the returned setup
+step, then hand control to the current workflow route.
+
+Use the user's language for conversation. Keep command and payload tokens
+unchanged.
+
+Run `context init [project-dir] [--name <name>] --language <language>`. Use the
+user's explicit language choice when present; otherwise pass `zh-CN` for a
+Chinese conversation and `en` for an English conversation. This explicit CLI
+value controls generated workspace instructions and starter templates. Never
+substitute `.` when `project-dir` was omitted; the default is `context/`. Use
+`--dev` only for an explicitly requested local-link test.
+Add `--debug` only when the user explicitly asks to trace this workspace. Debug
+mode is otherwise off by default.
+
+If init reports `init-target-nonempty`, explain that existing files would share
+the workspace root. Run the returned `--allow-nonempty` command only after
+explicit confirmation.
+
+Execute the returned setup command, enter the project root, and read its
+generated `AGENTS.md`. Then run `context status --format json`, adding
+`--managed` only for fully managed operation explicitly authorized in this
+conversation. Treat `workflow.current` as authoritative: read its required
+resources, execute only exact commands, honor unresolved human gates, and
+reevaluate status after each action.
+
+Do not add extra project-local agent setup or infer sources from the surrounding
+monorepo.

package/plugins/cursor/.cursor-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "context",
   "displayName": "C4A Context",
-  "version": "0.6.1",
+  "version": "0.6.3",
   "description": "Maintain a project-local knowledge workspace through init and next-step agent guidance.",
   "author": {
     "name": "Context4AI",
@@ -24,6 +24,5 @@
     "agent-skills",
     "citations"
   ],
-  "commands": "./commands/",
-  "skills": "./skills/"
+  "commands": "./commands/"
 }

package/plugins/cursor/README.md

@@ -6,8 +6,8 @@ Edit `packages/context-cli/plugin/` and rerun the build instead.
 
 Install shape:
 
-- Marketplace/GitHub plugin shape: this directory is a plugin root with `.cursor-plugin/plugin.json`, `commands/`, and `skills/`.
+- Marketplace/GitHub plugin shape: this directory is a plugin root with `.cursor-plugin/plugin.json` and `commands/`.
 - User entries are under `commands/`; Cursor command files are prefixed as `context-*` to avoid global slash-command collisions.
 - Local plugin fallback: symlink or copy this directory to `~/.cursor/plugins/local/context/` only when Marketplace import is unavailable.
 
-Do not copy these files into `.cursor/skills/` as the main install path. Cursor Marketplace installs this plugin root directly.
+Cursor Marketplace installs this plugin root directly.

package/plugins/cursor/commands/context-continue.md

@@ -10,27 +10,78 @@ Continue the Context workflow from the current workspace state.
 
 ## Workflow
 
-Use this as the conversational entry for an existing Context workspace. There is
-no `context continue` CLI primitive; the command runs lower-level `context ...`
-commands only when the workspace state requires them.
+Use this as the conversational entry for an existing Context workspace. There
+is no `context continue` CLI primitive. Without explicit fully managed
+authority, start with:
+
+```bash
+context status --format json
+```
+
+If the user explicitly asks to enable debugging, first run
+`context debug enable`. It sets `package.json` `context.debug=true` and records
+subsequent CLI and Agent Graph events only below `.tmp/context-runtime/debug/`.
+Do not enable it proactively; tracing is not workflow authority or evidence.
+
+When the user explicitly requests fully managed operation in this conversation,
+start with the managed loop instead of a manual status/action cycle:
+
+```bash
+context run --managed --until blocked-or-complete --format json
+```
+
+Never persist or reuse that authority in another conversation. While the
+request remains active, use `--managed` for every resumed status evaluation;
+stop using it when the conversation ends or the user revokes it.
 
 If the user is starting a new workspace or a new batch from a raw repository
 root, do not run `context status` first. Use the public Context init entry or
 `context init` to create the workspace, complete the init setup command, then
 return here from the initialized workspace.
 
-If `context status` reports `workspace-not-found` and points at a configured
-`context.workspaceDir`, do not keep working from the host repository root. Enter
-that workspace when it exists, or initialize it through the init workflow after
-confirming with the user.
+The managed loop is the default entry for an explicitly managed conversation,
+not an optional optimization. Pass an additional `--authority` only when the user explicitly granted that
+non-managed authority in this conversation. This loop executes only one
+revision-bound command at a time and re-evaluates after every receipt. It stops
+before read-only interpretation, project configuration, unresolved authority,
+diagnostics, or a non-unique command plan. On stop, resume from the returned
+`workflow.current`; do not derive a command from earlier steps.
 
 Language policy: explain, ask, confirm, and summarize in the user's current
 conversation language. Keep CLI commands, flags, paths, ids, status enum values,
 JSONL payload keys, `source_ref` values, and copied CLI output tokens unchanged.
 
-Use the procedure in `../skills/skill-continue-workflow/SKILL.md` end to end. It owns the
-status loop, safe mechanical next steps, source/scope gate, review gate, package
-gate, and final report rules.
+Treat `workflow.current` as the current-step authority:
+
+1. Read every `resources.required` item whose `read_state` is
+   `read-required`. Read a `path` directly; for a resource with `command`,
+   execute that command and read the returned file. Keep read receipts only in
+   the current conversation and pass the merged receipt set back with
+   `context status --resource-receipts @<file>`; an unchanged static digest or
+   matching dynamic Route revision then returns `read_state: current`.
+   Materializing a resource is not a read: use the returned
+   `after_read_receipts` only after reading the complete returned file. A
+   `context.source-body/*` resource is the complete captured Markdown body;
+   source indexes and heading metadata never replace it. The exact
+   `resources.after_read.command` returns the re-evaluated `workflow.current`;
+   continue from that response without an additional status call.
+2. At a Gate, keep conditional context phase-local. An `inspection_action`
+   Skill or Schema is read only when performing that pre-decision inspection;
+   a `resolution_action` Skill or Schema is read only after the user confirms
+   the Gate. Neither replaces ordinary `resources.required`.
+3. Execute only `commands` returned by the Route, preserving revision and
+   authority flags exactly. A command marked `after-human-confirmation` must
+   wait for the current Gate decision. Run a command whose
+   `execution.target` is `agent-host` as a top-level host action with the
+   host's external and credential access, not inside a restricted child
+   sandbox. Request host approval when required; never weaken credential
+   storage as a workaround.
+4. If `configuration` is present, edit only the named project file using the
+   selected resources as its contract.
+5. After every action or configuration change, run status again. The managed
+   `--until` loop performs this re-evaluation internally. A phase-local
+   `next_action` can continue that operation but never replaces the workspace
+   Route.
 
 Do not infer repo sources, extraction scope, review decisions, or package output
 choices from surrounding files. Do not call source-repo operations such as

package/plugins/cursor/commands/context-init.md

@@ -1,6 +1,6 @@
 ---
 description: "Initialize a Context knowledge workspace."
-argument-hint: "[project-dir] [--name <name>]"
+argument-hint: "[project-dir] [--name <name>] [--language en|zh-CN] [--debug]"
 allowed-tools: Bash(context:*), Bash(bun:*), Bash(cd *)
 ---
 
@@ -10,16 +10,31 @@ Initialize a Context knowledge workspace.
 
 ## Workflow
 
-Initialize a Context workspace with the global CLI, then continue only through
-safe mechanical setup steps until the first human decision gate.
+Initialize a Context workspace with the global CLI, complete the returned setup
+step, then hand control to the current workflow route.
 
-Language policy: explain, ask, confirm, and summarize in the user's current
-conversation language. Keep CLI commands, flags, file paths, package names,
-enum values, payload keys, and copied CLI output tokens unchanged.
+Use the user's language for conversation. Keep command and payload tokens
+unchanged.
 
-Use the procedure in `../skills/skill-init-workspace/SKILL.md` end to end. It owns
-the `context init` invocation, dependency install follow-up, generated
-`AGENTS.md` handoff, status handoff, and stop conditions.
+Run `context init [project-dir] [--name <name>] --language <language>`. Use the
+user's explicit language choice when present; otherwise pass `zh-CN` for a
+Chinese conversation and `en` for an English conversation. This explicit CLI
+value controls generated workspace instructions and starter templates. Never
+substitute `.` when `project-dir` was omitted; the default is `context/`. Use
+`--dev` only for an explicitly requested local-link test.
+Add `--debug` only when the user explicitly asks to trace this workspace. Debug
+mode is otherwise off by default.
 
-Do not add extra project-local agent setup. Do not infer repo sources or
-extraction scope from the surrounding monorepo after setup.
+If init reports `init-target-nonempty`, explain that existing files would share
+the workspace root. Run the returned `--allow-nonempty` command only after
+explicit confirmation.
+
+Execute the returned setup command, enter the project root, and read its
+generated `AGENTS.md`. Then run `context status --format json`, adding
+`--managed` only for fully managed operation explicitly authorized in this
+conversation. Treat `workflow.current` as authoritative: read its required
+resources, execute only exact commands, honor unresolved human gates, and
+reevaluate status after each action.
+
+Do not add extra project-local agent setup or infer sources from the surrounding
+monorepo.

package/plugins/skills/context-continue/SKILL.md

@@ -13,33 +13,83 @@ Public Context entry for agents that expose skills instead of slash commands.
 - Public entry: `context-continue`
 - Host command names are installation-specific; use the command or skill surfaced by the current host instead of deriving a filesystem path from an example name.
 - CLI primitive prefix: `context ...`
-- Internal procedures live under `references/internal-procedures/`; read each referenced file in full before following that step.
 
 ---
 
 ## Workflow
 
-Use this as the conversational entry for an existing Context workspace. There is
-no `context continue` CLI primitive; the command runs lower-level `context ...`
-commands only when the workspace state requires them.
+Use this as the conversational entry for an existing Context workspace. There
+is no `context continue` CLI primitive. Without explicit fully managed
+authority, start with:
+
+```bash
+context status --format json
+```
+
+If the user explicitly asks to enable debugging, first run
+`context debug enable`. It sets `package.json` `context.debug=true` and records
+subsequent CLI and Agent Graph events only below `.tmp/context-runtime/debug/`.
+Do not enable it proactively; tracing is not workflow authority or evidence.
+
+When the user explicitly requests fully managed operation in this conversation,
+start with the managed loop instead of a manual status/action cycle:
+
+```bash
+context run --managed --until blocked-or-complete --format json
+```
+
+Never persist or reuse that authority in another conversation. While the
+request remains active, use `--managed` for every resumed status evaluation;
+stop using it when the conversation ends or the user revokes it.
 
 If the user is starting a new workspace or a new batch from a raw repository
 root, do not run `context status` first. Use the public Context init entry or
 `context init` to create the workspace, complete the init setup command, then
 return here from the initialized workspace.
 
-If `context status` reports `workspace-not-found` and points at a configured
-`context.workspaceDir`, do not keep working from the host repository root. Enter
-that workspace when it exists, or initialize it through the init workflow after
-confirming with the user.
+The managed loop is the default entry for an explicitly managed conversation,
+not an optional optimization. Pass an additional `--authority` only when the user explicitly granted that
+non-managed authority in this conversation. This loop executes only one
+revision-bound command at a time and re-evaluates after every receipt. It stops
+before read-only interpretation, project configuration, unresolved authority,
+diagnostics, or a non-unique command plan. On stop, resume from the returned
+`workflow.current`; do not derive a command from earlier steps.
 
 Language policy: explain, ask, confirm, and summarize in the user's current
 conversation language. Keep CLI commands, flags, paths, ids, status enum values,
 JSONL payload keys, `source_ref` values, and copied CLI output tokens unchanged.
 
-Use the procedure in `references/internal-procedures/skill-continue-workflow.md` end to end. It owns the
-status loop, safe mechanical next steps, source/scope gate, review gate, package
-gate, and final report rules.
+Treat `workflow.current` as the current-step authority:
+
+1. Read every `resources.required` item whose `read_state` is
+   `read-required`. Read a `path` directly; for a resource with `command`,
+   execute that command and read the returned file. Keep read receipts only in
+   the current conversation and pass the merged receipt set back with
+   `context status --resource-receipts @<file>`; an unchanged static digest or
+   matching dynamic Route revision then returns `read_state: current`.
+   Materializing a resource is not a read: use the returned
+   `after_read_receipts` only after reading the complete returned file. A
+   `context.source-body/*` resource is the complete captured Markdown body;
+   source indexes and heading metadata never replace it. The exact
+   `resources.after_read.command` returns the re-evaluated `workflow.current`;
+   continue from that response without an additional status call.
+2. At a Gate, keep conditional context phase-local. An `inspection_action`
+   Skill or Schema is read only when performing that pre-decision inspection;
+   a `resolution_action` Skill or Schema is read only after the user confirms
+   the Gate. Neither replaces ordinary `resources.required`.
+3. Execute only `commands` returned by the Route, preserving revision and
+   authority flags exactly. A command marked `after-human-confirmation` must
+   wait for the current Gate decision. Run a command whose
+   `execution.target` is `agent-host` as a top-level host action with the
+   host's external and credential access, not inside a restricted child
+   sandbox. Request host approval when required; never weaken credential
+   storage as a workaround.
+4. If `configuration` is present, edit only the named project file using the
+   selected resources as its contract.
+5. After every action or configuration change, run status again. The managed
+   `--until` loop performs this re-evaluation internally. A phase-local
+   `next_action` can continue that operation but never replaces the workspace
+   Route.
 
 Do not infer repo sources, extraction scope, review decisions, or package output
 choices from surrounding files. Do not call source-repo operations such as