devflow-kit 3.2.0 → 3.3.0

package/dist/commands/self-review.md

@@ -14,7 +14,7 @@ Run Simplify agent and Scrutinize agent sequentially on changed files for post-i
 
 ### Phase 0: Context Gathering
 
-**Produces:** FILES_CHANGED, TASK_DESCRIPTION, DECISIONS_CONTEXT, FEATURE_KNOWLEDGE
+**Produces:** FILES_CHANGED, TASK_DESCRIPTION, DECISIONS_CONTEXT, FEATURE_KNOWLEDGE, HEAD_BEFORE
 
 Detect changed files and build context:
 
@@ -22,6 +22,7 @@ Detect changed files and build context:
 2. Else run `git diff --name-only HEAD` + `git diff --name-only --cached` to get staged + unstaged
 3. If no changes found, report "No changes to review" and exit
 4. Build TASK_DESCRIPTION from recent commit messages or branch name
+5. Record `HEAD_BEFORE` (`git rev-parse HEAD`) now, before Simplify runs — Phase 3 compares against it
 ### Load DECISIONS_CONTEXT
 
 The decisions ledger belongs to the repository, not to one checkout: in a linked worktree it lives in the main worktree, and a session started in a subdirectory reads the copy at the repository root. Locate it with ONE git call, run from the start directory — `WORKTREE_PATH` if provided, otherwise cwd (`devflow:worktree-support`):
@@ -100,7 +101,7 @@ If no KBs exist, no KBs are relevant, or `.devflow/features/` is absent, set `FE
 
 Pass `FEATURE_KNOWLEDGE` to Scrutinize agent.
 
-**Extract:** FILES_CHANGED (list), TASK_DESCRIPTION (string), DECISIONS_CONTEXT (string, optional), FEATURE_KNOWLEDGE (string, optional)
+**Extract:** FILES_CHANGED (list), TASK_DESCRIPTION (string), DECISIONS_CONTEXT (string, optional), FEATURE_KNOWLEDGE (string, optional), HEAD_BEFORE (40-hex SHA)
 
 ### Phase 1: Simplify agent (Code Refinement)
 
@@ -112,13 +113,14 @@ Spawn Simplify agent to refine code for clarity and consistency:
 Agent(subagent_type="Simplify", run_in_background=false):
 "TASK_DESCRIPTION: {task_description}
 FILES_CHANGED: {files_changed}
-Simplify and refine the code for clarity and consistency while preserving functionality."
+Simplify and refine the code for clarity and consistency while preserving functionality.
+Commit any improvements with a conventional-commit message."
 
 **Wait for completion.** Simplify agent commits changes directly.
 
 ### Phase 2: Scrutinize agent (9-Pillar Quality Gate)
 
-**Produces:** SCRUTINIZE_STATUS, SCRUTINIZE_CHANGES
+**Produces:** SCRUTINIZE_STATUS
 **Requires:** FILES_CHANGED, TASK_DESCRIPTION, DECISIONS_CONTEXT
 
 Spawn Scrutinize agent for quality evaluation and fixing:
@@ -132,17 +134,19 @@ Evaluate against 9-pillar framework. Fix P0/P1 issues. Return structured report.
 Follow devflow:apply-decisions to scan DECISIONS_CONTEXT and Read full ADR/PF bodies on demand. Skip if (none).
 Follow devflow:apply-feature-knowledge for FEATURE_KNOWLEDGE. Skip if (none)."
 
-**Wait for completion.** Extract: STATUS (PASS|FIXED|BLOCKED), changes_made (bool)
+**Wait for completion.** Extract: STATUS (PASS|FIXED|BLOCKED) from the `### Status` line
 
 ### Phase 3: Conditional Validation
 
 **Produces:** VALIDATION_RESULT
-**Requires:** SCRUTINIZE_CHANGES
+**Requires:** HEAD_BEFORE, SCRUTINIZE_STATUS
 
-If Scrutinize agent made changes (STATUS == FIXED):
+If STATUS is BLOCKED, skip this phase: the report (Phase 4) names the blocker.
+
+Run this phase only if HEAD moved — `git rev-parse HEAD` differs from `HEAD_BEFORE`, meaning Simplify or Scrutinize committed (Simplify alone counts, whatever Scrutinize's STATUS is). Otherwise skip it. Its scope is changed-only over what the two agents changed:
 
 Agent(subagent_type="Validate", run_in_background=false):
-"FILES_CHANGED: {scrutinize_modified_files}
+"FILES_CHANGED: {output of `git diff --name-only HEAD_BEFORE..HEAD`}
 VALIDATION_SCOPE: changed-only
 Run build, typecheck, lint, test on modified files"
 
@@ -208,7 +212,7 @@ If the settings line says `KNOWLEDGE=off`, skip write-back entirely. The machine
 **Step 2 — Evaluate whether write-back is warranted:**
 
 Only proceed if **at least one** of these is true:
-- This workflow changed files in a directory that is documented by an existing feature knowledge base (a documented area changed).
+- This workflow changed files in a directory that is documented by an existing feature knowledge base (a documented area changed). Knowledge bases are written through at that point, never on a background schedule.
 - This workflow surfaced durable, cross-cutting knowledge about a codebase area that would help future agents working in the same area — patterns, anti-patterns, integration points, gotchas not visible from a single file read.
 
 **Never spawn unconditionally.** If neither condition is met, skip write-back silently.
@@ -252,6 +256,7 @@ When the Knowledge agent reports `KB_COMMIT: skipped (detached HEAD)`, the files
 │
 ├─ Phase 0: Context gathering
 │  ├─ Git diff for changed files
+│  ├─ Record HEAD_BEFORE
 │  └─ Read index.md → DECISIONS_CONTEXT
 │
 ├─ Phase 1: Simplify agent
@@ -261,7 +266,7 @@ When the Knowledge agent reports `KB_COMMIT: skipped (detached HEAD)`, the files
 │  └─ 9-pillar quality gate (may fix and commit)
 │
 ├─ Phase 3: Validate agent (conditional)
-│  └─ If Scrutinize agent made changes, verify tests pass
+│  └─ If HEAD moved since HEAD_BEFORE (Simplify or Scrutinize committed), changed-only Validate over HEAD_BEFORE..HEAD
 │
 └─ Phase 4: Report
    └─ Display summary with pillar status
@@ -280,6 +285,6 @@ When the Knowledge agent reports `KB_COMMIT: skipped (detached HEAD)`, the files
 
 1. **Orchestration only** - Command spawns agents, doesn't do the work
 2. **Sequential execution** - Simplify agent must complete before Scrutinize agent
-3. **Validation gate** - If Scrutinize agent changes code, must pass validation
+3. **Validation gate** - If Simplify agent or Scrutinize agent committed, the changes must pass validation
 4. **Honest reporting** - Display actual agent outputs
 5. **Fail fast** - Stop on BLOCKED or validation failure

package/dist/core/agent-models.js

@@ -83,13 +83,16 @@ export const EFFORT_INHERIT = 'inherit';
  * count are unaffected.
  *
  * Shipped value of `memory`: `claude-sonnet-5-5` at `high` effort. User decision
- * 2026-10-08: memory quality is worth more than the cost saving of Haiku, which
- * replaces the plan's Haiku default. The worker does not read `agents.memory`
- * yet. Until it does, background-memory-update names this model as a literal in
- * its `claude -p --model` argument, and tests/agent-models-worker.test.ts holds
- * that literal equal to this row so the two cannot drift apart. Wiring the
- * worker to this map, and `--effort` behind a CLI version probe, is a separate
- * change.
+ * 2026-10-08: memory quality is worth more than the cost saving of Haiku.
+ *
+ * D-MEMORY-WORKER-LEAN: background-memory-update reads `agents.memory` from
+ * `~/.devflow/agent-models.json` at run time, validating `model` and `effort`
+ * field by field against the domain below, and passes `--effort` when the CLI
+ * version probe puts it at or above the lean-argv floor. A field it cannot use
+ * falls back to this row. The hook spells that fallback out for bash
+ * (`MEMORY_MODEL_DEFAULT`, `MEMORY_EFFORT_DEFAULT`, the alias and effort lists and
+ * the model-name rules), and tests/agent-models-worker.test.ts holds every one
+ * equal to this row and to the domain, so the two cannot drift apart.
  */
 export const WORKER_AGENTS = {
     memory: { model: 'claude-sonnet-5-5', effort: 'high' },

package/dist/core/learning-tuning-config.js

@@ -6,6 +6,14 @@ const VALID_MODELS = new Set(['opus', 'sonnet', 'haiku']);
 function isValidModel(value) {
     return typeof value === 'string' && VALID_MODELS.has(value);
 }
+/**
+ * D-LEARNING-SHIPPED-ROW: the default model is the model the Learning agent ships
+ * with, the `model:` line of src/assets/agents/learning.md. With no layer
+ * configuring a model, the spawn directive names none and that line decides, so a
+ * different default here would describe a run that never happens.
+ * tests/decisions/config.test.ts holds this value equal to the Learning row of the
+ * agent-config table, which a change of the shipped tier edits with the frontmatter.
+ */
 const DEFAULTS = {
     model: 'opus',
     debug: false,

package/dist/core/plugins.js

@@ -244,7 +244,10 @@ export const DEVFLOW_PLUGINS = [
         commands: ['/release'],
         agents: ['git', 'validate'],
         skills: ['git', 'worktree-support'],
-        requires: ['testing'],
+        // D-PRELOAD-TRIM: nothing in this plugin's corpus reads `testing` (Validate
+        // preloads only `worktree-support`), so the closure guard's reverse arm holds
+        // this list empty.
+        requires: [],
         rules: [],
     },
     {
@@ -253,7 +256,9 @@ export const DEVFLOW_PLUGINS = [
         commands: ['/self-review'],
         agents: ['simplify', 'scrutinize', 'validate', 'knowledge'],
         skills: ['quality-gates', 'software-design', 'worktree-support', 'feature-knowledge', 'apply-feature-knowledge'],
-        requires: ['apply-decisions', 'testing'],
+        // D-PRELOAD-TRIM: no agent, command or skill in this plugin's corpus names
+        // `testing` (Validate preloads only `worktree-support`), so it is not required here.
+        requires: ['apply-decisions'],
         rules: [],
     },
     {

package/dist/skills/git/references/tracker/github/gather-release-evidence.md

@@ -7,7 +7,7 @@ Load when the resolved tracker provider is `github` and the operation is `gather
 ### Process
 
 1a. **Last release tag.** Step 1's `git describe` can return a non-release marker tag. From `WORKTREE_PATH` (else cwd), run `node "$HOME/.devflow/scripts/release-trace.cjs" last-tag`: `LAST_TAG <tag>` ⇒ that tag is `{last_tag}`; `LAST_TAG none` ⇒ step 1's initial-commit rule; anything else ⇒ keep step 1's tag and report status `INDETERMINATE (last release tag unresolved)`.
-3a. **Closing-keyword rule.** A candidate follows, on the same line, a whitespace token matching `^\(?(close[sd]?|fix(e[sd])?|resolve[sd]?|refs):?$` (case-insensitive). Take the next token, plus each further token while the previous one ends in `,`. Split each on `,`, strip one leading `(` and every trailing character in `[.,;:)\]!?]`, drop empties, then apply step 5's anchored gate unchanged. Read each message as `git log --format=%B` lines.
+3a. **Closing-keyword rule.** A candidate follows, on the same line, a whitespace token matching `^\(?(close[sd]?|fix(e[sd])?|resolve[sd]?):?$` (case-insensitive). Take the next token, plus each further token while the previous one ends in `,`. Split each on `,`, strip one leading `(` and every trailing character in `[.,;:)\]!?]`, drop empties, then apply step 5's anchored gate unchanged. Read each message as `git log --format=%B` lines.
 3b. **This provider's history grammar** is `^#[1-9][0-9]{0,8}$`. A bare number is not a reference here either: a keyword-anchored candidate must carry the `#`, and step 4 renders every number it reads from a merged PR as `#{n}` before step 5's gate.
 4. If `gh` is authenticated and remote is reachable, resolve which issues the range's merged PRs close — **one listing, never one call per commit** — and merge the result with the commit-message set:
    - **Once, before the listing:** this repo's identity, `gh api 'repos/{owner}/{repo}' --jq '.owner.login + "/" + .name'`, and the tag's UTC date, `TAG_DATE=$(TZ=UTC git log -1 --date=format-local:%Y-%m-%d --format=%cd {last_tag})`, shape-gated `^[0-9]{4}-[0-9]{2}-[0-9]{2}$` — a local date can drop a PR merged just after the tag. If `TAG_DATE` fails this gate, treat it as **the listing fails** below: emit `TRACEABILITY: DEGRADED ({reason})` and go straight to that bullet's ≤25-PR fallback.

package/dist/skills/git/references/tracker/jira/gather-release-evidence.md

@@ -7,7 +7,7 @@ Load when the resolved tracker provider is `jira` and the operation is `gather-r
 ### Process
 
 1a. **Last release tag.** Step 1's `git describe` can return a non-release marker tag. From `WORKTREE_PATH` (else cwd), run `node "$HOME/.devflow/scripts/release-trace.cjs" last-tag`: `LAST_TAG <tag>` ⇒ that tag is `{last_tag}`; `LAST_TAG none` ⇒ step 1's initial-commit rule; anything else ⇒ keep step 1's tag and report status `INDETERMINATE (last release tag unresolved)`.
-3a. **Closing-keyword rule.** A candidate follows, on the same line, a whitespace token matching `^\(?(close[sd]?|fix(e[sd])?|resolve[sd]?|refs):?$` (case-insensitive). Take the next token, plus each further token while the previous one ends in `,`. Split each on `,`, strip one leading `(` and every trailing character in `[.,;:)\]!?]`, drop empties, then apply step 5's anchored gate unchanged. Read each message as `git log --format=%B` lines.
+3a. **Closing-keyword rule.** A candidate follows, on the same line, a whitespace token matching `^\(?(close[sd]?|fix(e[sd])?|resolve[sd]?):?$` (case-insensitive). Take the next token, plus each further token while the previous one ends in `,`. Split each on `,`, strip one leading `(` and every trailing character in `[.,;:)\]!?]`, drop empties, then apply step 5's anchored gate unchanged. Read each message as `git log --format=%B` lines.
 4. Resolve which issues the commit range closes:
    - **There is no closing-reference capability on this provider.** Emit `TRACEABILITY: DEGRADED (unsupported by jira)` once for the whole step and fall back to the commit-message set alone — the refs parsed out of the candidate references the agent extracted from the range's commit messages.
    - **This provider's history grammar** is `^[A-Z][A-Z0-9_]{1,9}-[1-9][0-9]{0,8}$`, and its KEY segment must equal the resolved project key after ASCII-upper normalisation — a well-formed key belonging to another project is a `TRACEABILITY: DEGRADED (foreign issue reference {ref})`, not a shipped issue.

package/dist/skills/git/references/tracker/linear/gather-release-evidence.md

@@ -7,7 +7,7 @@ Load when the resolved tracker provider is `linear` and the operation is `gather
 ### Process
 
 1a. **Last release tag.** Step 1's `git describe` can return a non-release marker tag. From `WORKTREE_PATH` (else cwd), run `node "$HOME/.devflow/scripts/release-trace.cjs" last-tag`: `LAST_TAG <tag>` ⇒ that tag is `{last_tag}`; `LAST_TAG none` ⇒ step 1's initial-commit rule; anything else ⇒ keep step 1's tag and report status `INDETERMINATE (last release tag unresolved)`.
-3a. **Closing-keyword rule.** A candidate follows, on the same line, a whitespace token matching `^\(?(close[sd]?|fix(e[sd])?|resolve[sd]?|refs):?$` (case-insensitive). Take the next token, plus each further token while the previous one ends in `,`. Split each on `,`, strip one leading `(` and every trailing character in `[.,;:)\]!?]`, drop empties, then apply step 5's anchored gate unchanged. Read each message as `git log --format=%B` lines.
+3a. **Closing-keyword rule.** A candidate follows, on the same line, a whitespace token matching `^\(?(close[sd]?|fix(e[sd])?|resolve[sd]?):?$` (case-insensitive). Take the next token, plus each further token while the previous one ends in `,`. Split each on `,`, strip one leading `(` and every trailing character in `[.,;:)\]!?]`, drop empties, then apply step 5's anchored gate unchanged. Read each message as `git log --format=%B` lines.
 4. Resolve which issues the commit range closes:
    - **There is no closing-reference capability on this provider.** Emit `TRACEABILITY: DEGRADED (unsupported by linear)` once for the whole step and fall back to the commit-message set alone — the references parsed out of the candidate references the agent extracted from the range's commit messages. The magic words this provider recognises in a pull-request body are the SERVER's own behaviour and are not a capability this operation can read back: a body that closed an issue leaves no signal here, which is precisely why this step degrades instead of guessing.
    - **This provider's history grammar is the TEAM-KEY form only** — `^[A-Z][A-Z0-9]{0,9}-[1-9][0-9]{0,8}$`, with its key segment equal to the resolved team key after ASCII-upper normalisation; a well-formed reference on another team is a `TRACEABILITY: DEGRADED (foreign issue reference {ref})`. The internal-id form is NOT admitted from history: a bare identifier carries no team, so nothing distinguishes one workspace's from another's.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "devflow-kit",
-  "version": "3.2.0",
+  "version": "3.3.0",
   "description": "A meta-harness for Claude Code — turns a single coding agent into an engineering team: orchestration, parallel review, persistent memory, self-learning, and graph workflows",
   "type": "module",
   "bin": {

package/src/assets/agents/code.md

@@ -2,17 +2,32 @@
 name: Code
 description: Autonomous task implementation on feature branch. Implements, tests, and commits.
 model: sonnet
+effort: high
 skills:
-  - devflow:software-design
   - devflow:git
-  - devflow:patterns
   - devflow:testing
   - devflow:test-driven-development
-  - devflow:dependency-research
-  - devflow:boundary-validation
   - devflow:worktree-support
   - devflow:apply-feature-knowledge
   - devflow:apply-decisions
+disallowedTools:
+  - Agent
+  - SendMessage
+  - NotebookEdit
+  - EnterWorktree
+  - ExitWorktree
+  - ArtifactComments
+  - ArtifactData
+  - TodoWrite
+  - AskUserQuestion
+  - TaskOutput
+  - ScheduleWakeup
+  - CronCreate
+  - CronDelete
+  - CronList
+  - RemoteTrigger
+  - PushNotification
+  - DesignSync
 ---
 
 # Code Agent
@@ -28,7 +43,7 @@ You receive from orchestrator:
 - **EXECUTION_PLAN**: Synthesized plan with steps, files, tests
 - **PATTERNS**: Codebase patterns to follow
 - **CREATE_PR**: Whether to create PR when done (true/false)
-- **OPERATION** (optional): `implement` (default) | `issue-fix` | `validation-fix` | `alignment-fix` | `qa-fix` | `pr-create` — selects operating mode (see below)
+- **OPERATION** (optional): `implement` (default when absent) | `issue-fix` | `validation-fix` | `alignment-fix` | `qa-fix` | `pr-create` | `ci-fix` | `edit` — selects operating mode (see below); every spawn passes it as the first prompt line
 - **ISSUES** (when OPERATION: issue-fix): Pre-classified issues from Triage agent with disposition FIX_NOW; do not re-litigate
 - **SCOPE** (when OPERATION: issue-fix): Blast-radius scope hint (Standard | Careful) per issue from Triage agent
 - **PUSH** (optional): `true` (default) | `false` — when false, commit only; orchestrator owns push/CI gate
@@ -53,6 +68,21 @@ You receive from orchestrator:
 - **HANDOFF_REQUIRED**: true if another Code agent follows this one
 - **HANDOFF_FILE** (optional): Path to branch-scoped handoff file for prior phase context (e.g., `.devflow/docs/handoff-feat-my-feature.md`)
 
+## Step 0: Mode Skills
+
+Four skills are not preloaded. Load one with `Skill(skill="devflow:<name>")` only when its cell in your `OPERATION` row holds, judged from the spawn's inputs and the files they name; `never` loads nothing. Triggers — **error**: business logic, a fallible operation or an error path; **surface**: an endpoint, route, CRUD, event handler, config or logging; **input**: parsing of external input (args, requests, files, env, stdin); **helper**: a new helper, utility, wrapper, parser or dependency.
+
+| Mode | devflow:software-design | devflow:patterns | devflow:boundary-validation | devflow:dependency-research |
+|---|---|---|---|---|
+| `implement` | the plan adds **error** | the plan adds **surface** | the plan adds **input** | the plan adds a **helper** |
+| `issue-fix` | the fix changes **error** | the fix changes **surface** | the fix changes **input** | the fix adds a **helper** |
+| `alignment-fix` | a misalignment is in **error** | a misalignment is in **surface** | a misalignment is in **input** | a misalignment needs a **helper** |
+| `qa-fix` | a scenario fails in **error** | a scenario fails in **surface** | a scenario fails in **input** | a scenario needs a **helper** |
+| `validation-fix` | never | never | never | never |
+| `pr-create` | never | never | never | never |
+| `ci-fix` | never | never | never | the fix adds or upgrades a dependency |
+| `edit` | never | never | never | never |
+
 ## Responsibilities
 
 1. **Orient on branch state** (always, before any implementation): If FEATURE_KNOWLEDGE provided, read for pre-computed feature context — patterns, anti-patterns, integration points. Use as starting point; verify against current code. Follow `devflow:apply-feature-knowledge`.
@@ -143,7 +173,7 @@ Run builds, typechecks, lints and tests in the foreground, each with an explicit
 
 When `OPERATION: issue-fix`, you are fixing pre-classified issues assigned FIX_NOW by the Triage agent. Do not re-litigate dispositions.
 
-**Inputs:** `ISSUES` (list of pre-classified FIX_NOW issues), `SCOPE` (Standard | Careful per issue), `PUSH: false` (always for issue-fix; orchestrator pushes after Verification Gate)
+**Inputs:** `ISSUES` (pre-classified FIX_NOW issues), `SCOPE` (Standard | Careful per issue; absent means Standard), `PUSH: false` (always for issue-fix; the orchestrator pushes after its final validation gate)
 
 **Protocol:**
 1. Same-file issues → one commit (never two Code agents editing the same file concurrently)
@@ -151,13 +181,12 @@ When `OPERATION: issue-fix`, you are fixing pre-classified issues assigned FIX_N
    - **Standard scope**: Fix directly following existing patterns
    - **Careful scope**: systematic protocol — understand (50+ lines context, callers/consumers) → plan → write failing regression test → implement → verify tests pass → commit
 3. **Regression test rule**: A regression fix without a failing-then-passing regression test is INCOMPLETE. Report BLOCKED rather than commit an unverified fix.
-4. Document verification commands run (build, test, typecheck) in a `## Verification` block in your output report.
-5. **Self-verification scope**: Run compile + the specific regression test for the fix only. The Phase 7 Verification Gate is the single authoritative full build/test run — do not re-run the full suite here.
+4. **Self-verification scope**: Run compile + the fix's regression test only. The orchestrator's final validation gate is the single authoritative full build/test run — do not re-run the full suite here.
 
-**Return report includes:**
+**Return report** (a Return block in the spawn replaces this shape):
 - Status: COMPLETE | PARTIAL | BLOCKED
 - Issues fixed with commit SHAs
-- `## Verification` block: commands run and results
+- `## Verification` block: commands run (build, test, typecheck) and results
 - Unresolved issues with blocker description
 
 ## Mode: validation-fix
@@ -178,7 +207,7 @@ When `OPERATION: alignment-fix`, you are fixing intent/plan misalignments identi
 
 **Protocol:**
 1. Fix only what is listed in `MISALIGNMENTS` — no scope expansion
-2. Commit and push; orchestrator re-runs Validate agent then Evaluate agent after each attempt (max 2 attempts total)
+2. Commit and push; orchestrator re-runs Evaluate agent after each attempt (max 2 attempts total)
 
 ## Mode: qa-fix
 
@@ -188,7 +217,7 @@ When `OPERATION: qa-fix`, you are fixing scenario-based acceptance test failures
 
 **Protocol:**
 1. Fix only what is listed in `QA_FAILURES` — no scope expansion
-2. Commit and push; orchestrator re-runs Validate agent then Test agent after each attempt (max 2 attempts total)
+2. Commit and push; orchestrator re-runs Test agent after each attempt (max 2 attempts total)
 
 ## Mode: pr-create
 
@@ -201,15 +230,39 @@ When `OPERATION: pr-create`, earlier Code agents have already committed the impl
 2. Run Responsibility 7 only — the PR body, the `## Related Issues`, `PR_EXCEPTIONS` and `PR_TEST_PLAN_BLOCK` paste gates and the D11 scrub — targeting `BASE_BRANCH`.
 3. Return the PR URL.
 
+## Mode: ci-fix
+
+When `OPERATION: ci-fix`, you are fixing the CI checks the ci-status gate reports as failing. Fix only the named checks.
+
+**Inputs:** `CI_FAILURES` (failing-check names from the ci-wait verdict line; fetch the logs yourself), `SCOPE: Fix only the named failing checks`, `PUSH: false`, `CREATE_PR: false`
+
+**Protocol:**
+1. A behavioural test failure follows the issue-fix regression-test rule; a lint, format or type failure is fixed directly
+2. Run each named check's command once over the batch, scoped to the touched files (Running commands block)
+3. Commit
+
+**Return:** status, commit SHAs, `## Verification` block, unresolved checks
+
+## Mode: edit
+
+When `OPERATION: edit`, you apply a mechanical change: a rename, a move or boilerplate that adds no behaviour.
+
+**Inputs:** `EDIT_SPEC` (the change and the files it covers), `SCOPE: no new behaviour`, `PUSH: false`
+
+**Protocol:**
+1. Apply the change to the listed files only; add no tests, since no behaviour changes
+2. Run the tests of the touched modules once (Running commands block)
+3. Commit
+
+**Return:** status, commit SHAs, `## Verification` block
+
 ## Principles
 
 1. **Work on feature branch** - All operations happen on the current feature branch
-2. **Branch orientation first** - Always orient on branch state before writing code; actual code is authoritative over summaries
-3. **Pattern discovery first** - Before writing code, find similar implementations and match their conventions
-4. **Be decisive** - Make confident implementation choices. Don't present alternatives or ask permission for tactical decisions
-5. **Follow existing patterns** - Match codebase style, don't invent new conventions
-6. **Small, focused changes** - Don't scope creep beyond the plan
-7. **Fail honestly** - If blocked, report clearly with what was completed
+2. **Orient, then match patterns** - Before writing code, orient on branch state and find similar implementations; match their conventions, don't invent new ones
+3. **Be decisive** - Make confident implementation choices. Don't present alternatives or ask permission for tactical decisions
+4. **Small, focused changes** - Don't scope creep beyond the plan
+5. **Fail honestly** - If blocked, report clearly with what was completed
 
 ## Output
 

package/src/assets/agents/design.md

@@ -2,12 +2,22 @@
 name: Design
 description: "Design analysis agent with preloaded mode skills. Modes: gap-analysis (completeness, architecture, security, performance, compliance, consistency, dependencies), design-review (anti-pattern detection)."
 model: opus
+effort: high
 skills:
   - devflow:worktree-support
   - devflow:apply-decisions
   - devflow:gap-analysis
   - devflow:design-review
   - devflow:apply-feature-knowledge
+tools:
+  - Read
+  - Grep
+  - Glob
+  - Bash
+  - Write
+  - Edit
+  - Skill
+  - StructuredOutput
 ---
 
 # Design Agent

package/src/assets/agents/diagnose.md

@@ -2,15 +2,18 @@
 name: Diagnose
 description: Proactive bug finding agent with static+semantic analysis. Focus-specific analysis across security, functional, integration, and usability categories.
 model: opus
+effort: medium
 skills:
-  - devflow:security
-  - devflow:reliability
-  - devflow:regression
-  - devflow:consistency
-  - devflow:complexity
   - devflow:worktree-support
   - devflow:apply-decisions
   - devflow:apply-feature-knowledge
+tools:
+  - Read
+  - Grep
+  - Glob
+  - Bash
+  - Write
+  - Skill
 ---
 
 # Diagnose Agent
@@ -34,12 +37,14 @@ The orchestrator provides:
 
 ## Focus Areas
 
-| Focus | What to Hunt |
-|-------|-------------|
-| `security` | Auth gaps, injection flaws, secrets exposure, insecure dependencies, validates static findings |
-| `functional` | Logic errors, off-by-one, race conditions, incorrect state transitions, unhandled nulls |
-| `integration` | API contract violations, incorrect HTTP status codes, serialization mismatches, missing retry/timeout |
-| `usability` | Missing error states, absent loading indicators, unhelpful error messages, broken form validation |
+| Focus | What to Hunt | Pattern skill (load on demand) |
+|-------|-------------|-------------------------------|
+| `security` | Auth gaps, injection flaws, secrets exposure, insecure dependencies, validates static findings | `devflow:security` |
+| `functional` | Logic errors, off-by-one, race conditions, incorrect state transitions, unhandled nulls | `devflow:regression`, `devflow:reliability`, `devflow:complexity` |
+| `integration` | API contract violations, incorrect HTTP status codes, serialization mismatches, missing retry/timeout | `devflow:regression`, `devflow:consistency` |
+| `usability` | Missing error states, absent loading indicators, unhelpful error messages, broken form validation | `devflow:consistency`, `devflow:reliability` |
+
+Before Step 1, invoke the Skill tool with `Skill(skill="devflow:…")` for each skill in the row for your FOCUS. If an invocation fails, continue with this methodology: the skill adds patterns but is not required.
 
 ## Apply Decisions
 

package/src/assets/agents/evaluate.md

@@ -2,10 +2,16 @@
 name: Evaluate
 description: Validates implementation aligns with original request and plan. Catches missed requirements, scope creep, and intent drift. Reports misalignments for Code agent to fix.
 model: opus
+effort: medium
 skills:
-  - devflow:software-design
   - devflow:worktree-support
   - devflow:apply-feature-knowledge
+tools:
+  - Read
+  - Grep
+  - Glob
+  - Bash
+  - Write
 ---
 
 # Evaluate Agent
@@ -22,27 +28,18 @@ You receive from orchestrator:
 
 **Worktree Support**: If `WORKTREE_PATH` is provided, follow the `devflow:worktree-support` skill for path resolution. If omitted, use cwd.
 
-- **FEATURE_KNOWLEDGE** (optional): Pre-computed feature area context for
-  acceptance verification. Check implementation against documented feature
-  patterns and anti-patterns. Follow `devflow:apply-feature-knowledge`.
+- **FEATURE_KNOWLEDGE** (optional): Pre-computed feature area context, used
+  only to understand what the request and acceptance criteria mean in this
+  feature area. Follow `devflow:apply-feature-knowledge`.
 
 ## Responsibilities
 
 1. **Understand intent**: Read ORIGINAL_REQUEST and EXECUTION_PLAN to understand what was requested
 2. **Review implementation**: Read FILES_CHANGED to understand what was built
-3. **Goal-backward verification**: Start from the user's observable goals. For each goal: trace backward through the implementation — is it wired into the running app → does it contain substantive logic → does the file/function exist? Report any goal failing at any depth.
-4. **Check artifact depth**: Classify each deliverable using this scale:
-
-   | Depth | Meaning | Example |
-   |-------|---------|---------|
-   | Exists | File/function created | Route file exists |
-   | Substantive | Contains real logic | Route has validation + DB call |
-   | Wired | Connected to running app | Route registered, imported, reachable |
-
-   Flag anything at "Exists" without reaching "Wired" as `incomplete`.
-5. **Check completeness**: Verify all plan steps implemented, all acceptance criteria met. If FEATURE_KNOWLEDGE is provided, verify implementation follows documented patterns and avoids documented anti-patterns for the feature area
-6. **Check scope**: Identify out-of-scope additions not justified by design improvements
-7. **Report misalignments**: Document issues with sufficient detail for Code agent to fix
+3. **Goal-backward verification**: Start from the user's observable goals. For each goal, ask whether the implementation delivers it. Report any goal that is not delivered.
+4. **Check completeness**: Verify all plan steps implemented, all acceptance criteria met
+5. **Check scope**: Identify out-of-scope additions not justified by design improvements
+6. **Report misalignments**: Document issues with sufficient detail for Code agent to fix
 
 **Gate ownership:** Run no build, test or lint command. Git read commands only. Only Validate runs the full suite.
 
@@ -72,11 +69,6 @@ Return structured alignment status:
 - Implementation solves: {1-sentence summary}
 - Alignment: aligned | drifted
 
-### Artifact Depth
-| Deliverable | Exists | Substantive | Wired | Status |
-|-------------|--------|-------------|-------|--------|
-| {feature}   | Y/N    | Y/N         | Y/N   | complete/incomplete/stub |
-
 ### Misalignments Found (if MISALIGNED)
 
 | Type | Description | Files | Suggested Fix |
@@ -85,7 +77,6 @@ Return structured alignment status:
 | scope_creep | {what's out of scope} | {file paths} | {remove or justify} |
 | incomplete | {what's partially done} | {file paths} | {what remains} |
 | intent_drift | {how intent drifted} | {file paths} | {how to realign} |
-| stub | {placeholder, not real logic} | {file paths} | {what real implementation needs} |
 
 ### Scope Check
 - Out-of-scope additions: {list or "None"}
@@ -106,14 +97,12 @@ Report cap: final message at most about 1,500 tokens; longer material goes to a
 - Out-of-scope additions not justified by design
 - Partial implementations
 - Intent drift
-- Stubs or placeholders passing as real implementations
 
 **Report as ALIGNED:**
 - All plan steps implemented
 - All acceptance criteria met
 - No unjustified scope additions
 - Implementation matches original intent
-- All deliverables reach "Wired" depth
 
 **Never:**
 - Modify code or create commits

package/src/assets/agents/knowledge.md

@@ -2,6 +2,7 @@
 name: Knowledge
 description: Structures codebase exploration into a feature knowledge base and registers it in the index cache
 model: sonnet
+effort: medium
 skills:
   - devflow:feature-knowledge
   - devflow:apply-feature-knowledge
@@ -12,6 +13,7 @@ tools:
   - Grep
   - Glob
   - Write
+  - Edit
   - Bash
 ---
 
@@ -45,13 +47,13 @@ tools:
 
 ## Direct Write Protocol
 
-Write BOTH files atomically — no intermediate result files, no external scripts:
+Write BOTH files atomically — no intermediate result files, no external scripts. Refresh an existing `KNOWLEDGE.md` or `index.md` with `Edit`, changing only the lines that differ; use `Write` only to create a file that does not exist yet.
 
 1. Ensure `{worktree}/.devflow/features/{slug}/` directory exists
-2. Write `KNOWLEDGE.md` to that directory
+2. Create `KNOWLEDGE.md` with `Write`, or refresh the existing one with `Edit`
 3. Read `{worktree}/.devflow/features/index.md` (tolerate ENOENT)
 4. Replace the `- **{slug}**` line if found; else append the new line
-5. Write `index.md` back
+5. Apply that change to `index.md` with `Edit`, or create the file with `Write` when it does not exist yet
 
 The frontmatter in KNOWLEDGE.md is always the authority. The index.md line is a discoverable cache.
 

package/src/assets/agents/learning.md

@@ -7,8 +7,6 @@ tools:
   - Bash
   - Glob
   - Grep
-skills:
-  - devflow:apply-decisions
 ---
 
 # Learning Agent
@@ -199,9 +197,9 @@ prevented by existing tooling.
 - Pitfall = a non-obvious failure mode with a transferable lesson that the next contributor
   cannot recover from the code alone.
 
-**Already encoded?** Search the repository (Grep, Glob) for a test, a guard, CLAUDE.md, a
-rules file or a prompt that already states or enforces the lesson. If one does, record
-nothing.
+**Already encoded?** Search the repository with `git grep -P` and `find` for a test, a
+guard, CLAUDE.md, a rules file or a prompt that already states or enforces the lesson. If
+one does, record nothing.
 
 **ADR-XOR-PF (hard rule)**: one incident yields exactly one of an ADR or a PF — never both.
 Concrete failure → PF; forward-looking architectural choice → ADR.
@@ -281,7 +279,7 @@ when unsure, Keep.
 1. **Encoded** — the codebase now enforces or states the rule, by a strict bar: a test or
    guard that fails on a new violation anywhere in the entry's scope, or the rule stated in
    CLAUDE.md, a rules file, or a prompt loaded for all work in that scope. One JSDoc line
-   does not count, and neither does a test pinning one instance. Find it with Grep,
+   does not count, and neither does a test pinning one instance. Find it with `git grep -P`,
    confirm it at the ref, then retire the entry with the file and a line of it:
 
    ```bash

package/src/assets/agents/research.md

@@ -2,10 +2,29 @@
 name: Research
 description: Multi-type research agent with dynamic skill loading. Receives research type, loads domain-specific skill, produces structured findings.
 model: opus
+effort: medium
 skills:
   - devflow:worktree-support
   - devflow:apply-decisions
   - devflow:apply-feature-knowledge
+disallowedTools:
+  - Agent
+  - SendMessage
+  - NotebookEdit
+  - EnterWorktree
+  - ExitWorktree
+  - ArtifactComments
+  - ArtifactData
+  - TodoWrite
+  - AskUserQuestion
+  - TaskOutput
+  - ScheduleWakeup
+  - CronCreate
+  - CronDelete
+  - CronList
+  - RemoteTrigger
+  - PushNotification
+  - DesignSync
 ---
 
 # Research Agent

package/src/assets/agents/review.md

@@ -2,11 +2,21 @@
 name: Review
 description: Universal code review agent with parameterized focus. Dynamically loads pattern skill for assigned focus area.
 model: opus
+effort: high
 skills:
   - devflow:review-methodology
   - devflow:worktree-support
   - devflow:apply-decisions
   - devflow:apply-feature-knowledge
+tools:
+  - Read
+  - Grep
+  - Glob
+  - Bash
+  - Write
+  - Edit
+  - Skill
+  - StructuredOutput
 ---
 
 # Review Agent