devflow-kit 3.2.0 → 3.4.0

package/dist/commands/plan.md

@@ -109,14 +109,25 @@ If the user says "skip" or "just proceed" — skip remaining questions, present
 
 #### Phase 2: Orient + Load Decisions
 
-**Produces:** SKIM_CONTEXT, DECISIONS_CONTEXT, FEATURE_KNOWLEDGE
+**Produces:** SKIM_CONTEXT, DECISIONS_CONTEXT, FEATURE_KNOWLEDGE, FEATURE_KNOWLEDGE_RULES
 **Requires:** CONFIRMED_SCOPE
 
+**Resolve the settings line** once per worktree root, reusing a line this run already resolved for the same root. `{root}` is the worktree the values are for — the repository root when the run has one worktree:
+
+```bash
+node "$HOME/.devflow/scripts/resolve-settings.cjs" "{root}" 2>/dev/null; echo "exit=$?"
+```
+
+Accept the output only when it is exactly two lines: `exit=0` last and, before it, one line of the form `TRACKER=<github|jira|linear> TRACKER_SOURCE=<project|personal|machine|default> TRACKER_WARN=<none|mismatch|invalid> SITE=<none|https://<host>> KEY=<none|<key>> REVIEW_PUBLICATION=<off|auto|full> COMPLIANCE=<off|generic|<id>[,<id>…]> MEMORY=<on|off> LEARNING=<on|off> KNOWLEDGE=<on|off>` — these fields, in this order, nothing else, where `<host>` is a lowercase dotted host name alone, `<key>` is 2–10 of `A-Z`, `0-9` and `_` starting with a letter, and each `<id>` is one of `gdpr`, `hipaa`, `pci-dss`, `soc2`, `iso-27001`, `sox`. **Anything else** (a non-zero exit, no line, extra text, or a missing, reordered or unlisted field or value) ⇒ use `TRACKER=github TRACKER_SOURCE=default TRACKER_WARN=invalid SITE=none KEY=none REVIEW_PUBLICATION=off COMPLIANCE=generic MEMORY=on LEARNING=on KNOWLEDGE=off` instead.
+
+The accepted line is the only source of these values: the script alone folds the committed `.devflow/project.json`, the personal `.devflow/config.json` and the machine manifest.
+
 Spawn Skim agent for codebase context:
 
 ```
 Agent(subagent_type="Skim"):
 "Orient in codebase for design planning: {feature/issues}
+LEARNING: {LEARNING from the settings line}
 Run rskim on source directories (NOT repo root) to identify:
 - Existing patterns and conventions in the affected area
 - File structure and module boundaries
@@ -135,6 +146,8 @@ and using its one-line output. If the command fails (outside a git repository),
 
 ### Load DECISIONS_CONTEXT
 
+When the settings line says `LEARNING=off`, set `DECISIONS_CONTEXT` to `(none)` and skip this step, locating no ledger and reading no index.
+
 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`):
 
 ```bash
@@ -162,7 +175,7 @@ The index is one direct file read, written at render time by `render-decisions.c
 
 When `DECISIONS_CONTEXT` is not `(none)`, follow `devflow:apply-decisions` to scan the index, identify plausibly-relevant entries, Read full entry bodies on demand, and cite verbatim IDs in downstream agent prompts and reasoning.
 
-This produces a compact index of active ADR/PF entries. Pass Skim agent context and `DECISIONS_CONTEXT` to all subsequent agents — prior decisions constrain design, known pitfalls inform gap analysis. Agents use `devflow:apply-decisions` to Read full entry bodies on demand.
+This produces a compact index of active ADR/PF entries. Pass the Skim agent context to all subsequent agents. Pass `DECISIONS_CONTEXT` to the Design agents of the gap-analysis phase — prior decisions constrain design, known pitfalls inform gap analysis. Design agents use `devflow:apply-decisions` to Read full entry bodies on demand.
 
 ### Load Feature Knowledge
 
@@ -192,31 +205,41 @@ Glob `{worktree}/.devflow/features/*/KNOWLEDGE.md`. For each file found, read on
 
 Match the current task area and description against each index line (or frontmatter `description` + `directories` on fallback). Select entries whose documented area overlaps the current task. This is a relevance judgment — prefer specificity over breadth.
 
-**Step 4 — Read selected KBs:**
+**Step 4 — Read each selected KB's Rules:**
+
+For each selected entry, `{kb}` is `{worktree}/.devflow/features/{slug}/KNOWLEDGE.md`:
 
-For each selected entry, read `{worktree}/.devflow/features/{slug}/KNOWLEDGE.md` in full. When the KB content contradicts the current code you observe, **trust the code** — the code is the freshness mechanism; the KB may lag behind.
+1. List its `##` headings with line numbers through Bash: `command grep -n '^## ' "{kb}"`. This only locates sections; the text of a KB comes from the Read view alone.
+2. Read the `## Rules` range (its line to the next heading) with the Read tool, using `offset` and `limit`, and choose the one to three bullets most relevant to the current task. The choice is yours, made per KB.
+3. If the KB has no `## Rules` section, choose one to three entries from its `## Anti-Patterns` or `## Gotchas` range the same way, and label them by that section's name instead of an ID.
 
-**Step 5 — Set FEATURE_KNOWLEDGE:**
+When a KB contradicts the code you observe, **trust the code** — the code is the freshness mechanism; the KB may lag behind. A missing Rules section, a missing heading list and `(none)` are legitimate states, not errors.
 
-Concatenate the selected KNOWLEDGE.md files under slug headers:
+**Step 5 — Set FEATURE_KNOWLEDGE and FEATURE_KNOWLEDGE_RULES:**
+
+Write one block per selected KB. Paste each bullet verbatim from the Read view, never from a shell view. The path is relative to the checkout root; an agent resolves it under `WORKTREE_PATH` when one is provided.
 
 ```
 --- Feature knowledge: {slug} ---
-{full KNOWLEDGE.md content}
+KB: .devflow/features/{slug}/KNOWLEDGE.md
+Rules:
+- **KB-AP-2** {bullet text, verbatim}
+- **KB-INV-1** {bullet text, verbatim}
+Headings: L5 Rules · L40 Overview · L62 Anti-Patterns · L118 Key Files
 ```
 
-If no KBs exist, no KBs are relevant, or `.devflow/features/` is absent, set `FEATURE_KNOWLEDGE` to `(none)`.
+A KB with no Rules section labels its entries `Rules ({section name}):` and gives them no ID. `FEATURE_KNOWLEDGE` is these blocks; `FEATURE_KNOWLEDGE_RULES` is the same blocks without the `Headings:` line. Both come from this one selection, and each spawn names the variable its recipient takes. If no KBs exist, no KBs are relevant, or `.devflow/features/` is absent, set both to `(none)`.
 
-**One git call, then direct file reads — no `.cjs` script.** After resolving `{worktree}`, this step is 1 index read (or N frontmatter reads on fallback), bounded by KB count.
+**One git call, then direct reads — no `.cjs` script.** After resolving `{worktree}`, this step is 1 index read (or N frontmatter reads on fallback), plus one heading listing and one Rules read per selected KB, bounded by KB count.
 
-Pass `FEATURE_KNOWLEDGE` alongside `DECISIONS_CONTEXT` to Explore and Design agents.
+Pass `FEATURE_KNOWLEDGE` to Explore and Design agents. Pass `DECISIONS_CONTEXT` to Design agents only.
 
 #### Phase 3: Explore Requirements (Parallel)
 
 **Produces:** EXPLORE_OUTPUTS
-**Requires:** SKIM_CONTEXT, DECISIONS_CONTEXT
+**Requires:** SKIM_CONTEXT
 
-Spawn 4 Explore agents **in a single message**, each with Skim agent context, `DECISIONS_CONTEXT` (from Phase 2), and `FEATURE_KNOWLEDGE` (from Phase 2). Include instructions: "follow `devflow:apply-decisions` for DECISIONS_CONTEXT" and "The FEATURE_KNOWLEDGE is a baseline — VALIDATE, EXTEND, and CORRECT it, don't repeat it. Focus on areas the feature knowledge doesn't cover and changes since it was last updated." Ask each agent for a final report of at most about 1,500 tokens: findings with file:line references, not file dumps.
+Spawn 4 Explore agents **in a single message**, each with Skim agent context and `FEATURE_KNOWLEDGE: {feature_knowledge}` (from Phase 2). Include the instruction: "The FEATURE_KNOWLEDGE is a baseline — VALIDATE, EXTEND, and CORRECT it. For anything it already covers, cite its KB IDs (`{slug} KB-AP-n`) instead of restating the text. Focus on areas the feature knowledge doesn't cover and changes since it was last updated." Ask each agent for a final report of at most about 1,500 tokens: findings with file:line references, not file dumps.
 
 | Focus | Thoroughness | Find |
 |-------|-------------|------|
@@ -249,17 +272,7 @@ Combine into: user needs, similar features, constraints, failure modes"
 **Produces:** GAP_OUTPUTS, COMPLIANCE_ACTIVE, COMPLIANCE_FRAMEWORKS
 **Requires:** EXPLORATION_SYNTHESIS, SKIM_CONTEXT, DECISIONS_CONTEXT
 
-**Resolve the compliance lens** for each worktree root, from its settings line (every framework reference is installed on every machine, so no file check decides it):
-
-**Resolve the settings line** once per worktree root, reusing a line this run already resolved for the same root. `{root}` is the worktree the values are for — the repository root when the run has one worktree:
-
-```bash
-node "$HOME/.devflow/scripts/resolve-settings.cjs" "{root}" 2>/dev/null; echo "exit=$?"
-```
-
-Accept the output only when it is exactly two lines: `exit=0` last and, before it, one line of the form `TRACKER=<github|jira|linear> TRACKER_SOURCE=<project|personal|machine|default> TRACKER_WARN=<none|mismatch|invalid> SITE=<none|https://<host>> KEY=<none|<key>> REVIEW_PUBLICATION=<off|auto|full> COMPLIANCE=<off|generic|<id>[,<id>…]> MEMORY=<on|off> LEARNING=<on|off> KNOWLEDGE=<on|off>` — these fields, in this order, nothing else, where `<host>` is a lowercase dotted host name alone, `<key>` is 2–10 of `A-Z`, `0-9` and `_` starting with a letter, and each `<id>` is one of `gdpr`, `hipaa`, `pci-dss`, `soc2`, `iso-27001`, `sox`. **Anything else** (a non-zero exit, no line, extra text, or a missing, reordered or unlisted field or value) ⇒ use `TRACKER=github TRACKER_SOURCE=default TRACKER_WARN=invalid SITE=none KEY=none REVIEW_PUBLICATION=off COMPLIANCE=generic MEMORY=on LEARNING=on KNOWLEDGE=off` instead.
-
-The accepted line is the only source of these values: the script alone folds the committed `.devflow/project.json`, the personal `.devflow/config.json` and the machine manifest.
+**Resolve the compliance lens** for each worktree root, from its settings line — the line resolved above for that root, by the settings block when this run has not yet resolved it (every framework reference is installed on every machine, so no file check decides it).
 
 **Set the compliance lens** from that line: `COMPLIANCE_FRAMEWORKS` is the settings line's `COMPLIANCE` with `generic` written `none`: `off`, `none`, or the framework ids the machine and this repository declare.
 
@@ -386,7 +399,7 @@ Combine into: patterns to follow, integration points, reusable code, edge cases"
 #### Phase 10: Plan Implementation (Parallel)
 
 **Produces:** PLAN_OUTPUTS
-**Requires:** IMPL_EXPLORATION_SYNTHESIS, GAP_SYNTHESIS, DECISIONS_CONTEXT
+**Requires:** IMPL_EXPLORATION_SYNTHESIS, GAP_SYNTHESIS
 
 Spawn 3 Plan agents **in a single message**, each with implementation exploration synthesis. Ask each agent for a final report of at most about 1,500 tokens: the plan itself, not a restatement of the exploration.
 

package/dist/commands/release.md

@@ -52,7 +52,19 @@ Read `.release/RELEASE-FLOW.md`:
 
 ### Phase 1b: Load Context
 
-**Produces:** DECISIONS_CONTEXT, FEATURE_KNOWLEDGE
+**Produces:** DECISIONS_CONTEXT, FEATURE_KNOWLEDGE, FEATURE_KNOWLEDGE_RULES
+
+**Resolve the settings line** once per worktree root, reusing a line this run already resolved for the same root. `{root}` is the worktree the values are for — the repository root when the run has one worktree:
+
+```bash
+node "$HOME/.devflow/scripts/resolve-settings.cjs" "{root}" 2>/dev/null; echo "exit=$?"
+```
+
+Accept the output only when it is exactly two lines: `exit=0` last and, before it, one line of the form `TRACKER=<github|jira|linear> TRACKER_SOURCE=<project|personal|machine|default> TRACKER_WARN=<none|mismatch|invalid> SITE=<none|https://<host>> KEY=<none|<key>> REVIEW_PUBLICATION=<off|auto|full> COMPLIANCE=<off|generic|<id>[,<id>…]> MEMORY=<on|off> LEARNING=<on|off> KNOWLEDGE=<on|off>` — these fields, in this order, nothing else, where `<host>` is a lowercase dotted host name alone, `<key>` is 2–10 of `A-Z`, `0-9` and `_` starting with a letter, and each `<id>` is one of `gdpr`, `hipaa`, `pci-dss`, `soc2`, `iso-27001`, `sox`. **Anything else** (a non-zero exit, no line, extra text, or a missing, reordered or unlisted field or value) ⇒ use `TRACKER=github TRACKER_SOURCE=default TRACKER_WARN=invalid SITE=none KEY=none REVIEW_PUBLICATION=off COMPLIANCE=generic MEMORY=on LEARNING=on KNOWLEDGE=off` instead.
+
+The accepted line is the only source of these values: the script alone folds the committed `.devflow/project.json`, the personal `.devflow/config.json` and the machine manifest.
+
+When the settings line says `LEARNING=off`, set `DECISIONS_CONTEXT` to `(none)` and skip this step, locating no ledger and reading no index.
 
 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`):
 
@@ -70,9 +82,62 @@ This is the rule the learning hooks apply (D-LEDGER-MAIN-WORKTREE, D-PROMPT-ROOT
 
 Read `{ledger}/.devflow/learning/index.md`. If the file is absent or empty, set `DECISIONS_CONTEXT` to `(none)`; otherwise use the file content as `DECISIONS_CONTEXT`.
 
-Load feature knowledge: Attempt to read `.devflow/features/index.md` (the regenerable cache). If absent or empty, glob `.devflow/features/*/KNOWLEDGE.md` and read each file's YAML frontmatter (`name`, `description`, `directories`) as the relevance surface. Pick release-relevant KBs by matching their documented area against the release context. For each selected KB, read the full `KNOWLEDGE.md` — trust current code over KB content on any mismatch. Concatenate under slug headers and set `FEATURE_KNOWLEDGE` (or `(none)` if no KBs exist or none are relevant). No `index.json`, no subprocess, no `.cjs` script.
+### Load Feature Knowledge
+
+Resolve `{worktree}` as the checkout's toplevel, because feature knowledge bases are committed with the branch (D-PROMPT-ROOT): from the start directory — `WORKTREE_PATH` if provided, otherwise cwd (`devflow:worktree-support`) — run
+
+```bash
+git -C "{start}" rev-parse --show-toplevel
+```
+
+and use its one-line output. If the command fails (outside a git repository), `{worktree}` is the start directory itself. All paths below are relative to `{worktree}`.
+
+**Step 1 — Read the index cache:**
+
+Attempt to read `{worktree}/.devflow/features/index.md`. Each line follows the format:
+
+```
+- **{slug}** — {areas} — {Use-when description}
+```
+
+If `index.md` exists and contains at least one entry line, use it for relevance matching.
+
+**Step 2 — Fallback: glob frontmatter (if `index.md` is absent or empty):**
+
+Glob `{worktree}/.devflow/features/*/KNOWLEDGE.md`. For each file found, read only its YAML frontmatter block (between the opening and closing `---` delimiters). The frontmatter fields `name`, `description`, and `directories` are the authoritative relevance surface — `index.md` is only a cache.
+
+**Step 3 — Pick relevant KBs:**
+
+Match the current task area and description against each index line (or frontmatter `description` + `directories` on fallback). Select entries whose documented area overlaps the current task. This is a relevance judgment — prefer specificity over breadth.
+
+**Step 4 — Read each selected KB's Rules:**
+
+For each selected entry, `{kb}` is `{worktree}/.devflow/features/{slug}/KNOWLEDGE.md`:
+
+1. List its `##` headings with line numbers through Bash: `command grep -n '^## ' "{kb}"`. This only locates sections; the text of a KB comes from the Read view alone.
+2. Read the `## Rules` range (its line to the next heading) with the Read tool, using `offset` and `limit`, and choose the one to three bullets most relevant to the current task. The choice is yours, made per KB.
+3. If the KB has no `## Rules` section, choose one to three entries from its `## Anti-Patterns` or `## Gotchas` range the same way, and label them by that section's name instead of an ID.
+
+When a KB contradicts the code you observe, **trust the code** — the code is the freshness mechanism; the KB may lag behind. A missing Rules section, a missing heading list and `(none)` are legitimate states, not errors.
+
+**Step 5 — Set FEATURE_KNOWLEDGE and FEATURE_KNOWLEDGE_RULES:**
+
+Write one block per selected KB. Paste each bullet verbatim from the Read view, never from a shell view. The path is relative to the checkout root; an agent resolves it under `WORKTREE_PATH` when one is provided.
+
+```
+--- Feature knowledge: {slug} ---
+KB: .devflow/features/{slug}/KNOWLEDGE.md
+Rules:
+- **KB-AP-2** {bullet text, verbatim}
+- **KB-INV-1** {bullet text, verbatim}
+Headings: L5 Rules · L40 Overview · L62 Anti-Patterns · L118 Key Files
+```
+
+A KB with no Rules section labels its entries `Rules ({section name}):` and gives them no ID. `FEATURE_KNOWLEDGE` is these blocks; `FEATURE_KNOWLEDGE_RULES` is the same blocks without the `Headings:` line. Both come from this one selection, and each spawn names the variable its recipient takes. If no KBs exist, no KBs are relevant, or `.devflow/features/` is absent, set both to `(none)`.
+
+**One git call, then direct reads — no `.cjs` script.** After resolving `{worktree}`, this step is 1 index read (or N frontmatter reads on fallback), plus one heading listing and one Rules read per selected KB, bounded by KB count.
 
-Pass both to all subsequent agents via their input contracts.
+Pass `DECISIONS_CONTEXT` and `FEATURE_KNOWLEDGE` only to agents whose contract declares them; the Validate and Git agents this command spawns do not.
 
 ### Phase 1c: Resolve the Evidence Policy
 
@@ -230,7 +295,7 @@ On completion:
 │  └─ Read .release/RELEASE-FLOW.md (learned) or proceed to detect (fresh)
 │
 ├─ Phase 1b: Load Context
-│  └─ Load DECISIONS_CONTEXT and FEATURE_KNOWLEDGE for downstream agents
+│  └─ Load DECISIONS_CONTEXT and FEATURE_KNOWLEDGE for the agents that declare them
 │
 ├─ Phase 2: Detect Release Process (first run only)
 │  └─ Tiered scan: package.json, CI workflows, git history

package/dist/commands/research.md

@@ -31,7 +31,7 @@ $ARGUMENTS
 
 ### Phase 1: Load Decisions (Orchestrator-Local)
 
-**Produces:** DECISIONS_CONTEXT, FEATURE_KNOWLEDGE
+**Produces:** DECISIONS_CONTEXT, FEATURE_KNOWLEDGE, FEATURE_KNOWLEDGE_RULES
 
 **Docs root (D-DOCS-ROOT).** Every `.devflow/docs/` path this command reads or writes lives at the checkout's toplevel, never under the directory the session started in. Resolve `{worktree}` from the start directory — `WORKTREE_PATH` if provided, otherwise cwd (`devflow:worktree-support`) — by running
 
@@ -41,8 +41,20 @@ git -C "{start}" rev-parse --show-toplevel
 
 and using its one-line output. If the command fails (outside a git repository), `{worktree}` is the start directory itself. Every docs path below is written `{worktree}/.devflow/docs/…`; a repo-relative docs path handed to an agent always travels with a `WORKTREE_PATH` naming the checkout it is relative to.
 
+**Resolve the settings line** once per worktree root, reusing a line this run already resolved for the same root. `{root}` is the worktree the values are for — the repository root when the run has one worktree:
+
+```bash
+node "$HOME/.devflow/scripts/resolve-settings.cjs" "{root}" 2>/dev/null; echo "exit=$?"
+```
+
+Accept the output only when it is exactly two lines: `exit=0` last and, before it, one line of the form `TRACKER=<github|jira|linear> TRACKER_SOURCE=<project|personal|machine|default> TRACKER_WARN=<none|mismatch|invalid> SITE=<none|https://<host>> KEY=<none|<key>> REVIEW_PUBLICATION=<off|auto|full> COMPLIANCE=<off|generic|<id>[,<id>…]> MEMORY=<on|off> LEARNING=<on|off> KNOWLEDGE=<on|off>` — these fields, in this order, nothing else, where `<host>` is a lowercase dotted host name alone, `<key>` is 2–10 of `A-Z`, `0-9` and `_` starting with a letter, and each `<id>` is one of `gdpr`, `hipaa`, `pci-dss`, `soc2`, `iso-27001`, `sox`. **Anything else** (a non-zero exit, no line, extra text, or a missing, reordered or unlisted field or value) ⇒ use `TRACKER=github TRACKER_SOURCE=default TRACKER_WARN=invalid SITE=none KEY=none REVIEW_PUBLICATION=off COMPLIANCE=generic MEMORY=on LEARNING=on KNOWLEDGE=off` instead.
+
+The accepted line is the only source of these values: the script alone folds the committed `.devflow/project.json`, the personal `.devflow/config.json` and the machine manifest.
+
 ### Load DECISIONS_CONTEXT
 
+When the settings line says `LEARNING=off`, set `DECISIONS_CONTEXT` to `(none)` and skip this step, locating no ledger and reading no index.
+
 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`):
 
 ```bash
@@ -100,22 +112,32 @@ Glob `{worktree}/.devflow/features/*/KNOWLEDGE.md`. For each file found, read on
 
 Match the current task area and description against each index line (or frontmatter `description` + `directories` on fallback). Select entries whose documented area overlaps the current task. This is a relevance judgment — prefer specificity over breadth.
 
-**Step 4 — Read selected KBs:**
+**Step 4 — Read each selected KB's Rules:**
+
+For each selected entry, `{kb}` is `{worktree}/.devflow/features/{slug}/KNOWLEDGE.md`:
 
-For each selected entry, read `{worktree}/.devflow/features/{slug}/KNOWLEDGE.md` in full. When the KB content contradicts the current code you observe, **trust the code** — the code is the freshness mechanism; the KB may lag behind.
+1. List its `##` headings with line numbers through Bash: `command grep -n '^## ' "{kb}"`. This only locates sections; the text of a KB comes from the Read view alone.
+2. Read the `## Rules` range (its line to the next heading) with the Read tool, using `offset` and `limit`, and choose the one to three bullets most relevant to the current task. The choice is yours, made per KB.
+3. If the KB has no `## Rules` section, choose one to three entries from its `## Anti-Patterns` or `## Gotchas` range the same way, and label them by that section's name instead of an ID.
 
-**Step 5 — Set FEATURE_KNOWLEDGE:**
+When a KB contradicts the code you observe, **trust the code** — the code is the freshness mechanism; the KB may lag behind. A missing Rules section, a missing heading list and `(none)` are legitimate states, not errors.
 
-Concatenate the selected KNOWLEDGE.md files under slug headers:
+**Step 5 — Set FEATURE_KNOWLEDGE and FEATURE_KNOWLEDGE_RULES:**
+
+Write one block per selected KB. Paste each bullet verbatim from the Read view, never from a shell view. The path is relative to the checkout root; an agent resolves it under `WORKTREE_PATH` when one is provided.
 
 ```
 --- Feature knowledge: {slug} ---
-{full KNOWLEDGE.md content}
+KB: .devflow/features/{slug}/KNOWLEDGE.md
+Rules:
+- **KB-AP-2** {bullet text, verbatim}
+- **KB-INV-1** {bullet text, verbatim}
+Headings: L5 Rules · L40 Overview · L62 Anti-Patterns · L118 Key Files
 ```
 
-If no KBs exist, no KBs are relevant, or `.devflow/features/` is absent, set `FEATURE_KNOWLEDGE` to `(none)`.
+A KB with no Rules section labels its entries `Rules ({section name}):` and gives them no ID. `FEATURE_KNOWLEDGE` is these blocks; `FEATURE_KNOWLEDGE_RULES` is the same blocks without the `Headings:` line. Both come from this one selection, and each spawn names the variable its recipient takes. If no KBs exist, no KBs are relevant, or `.devflow/features/` is absent, set both to `(none)`.
 
-**One git call, then direct file reads — no `.cjs` script.** After resolving `{worktree}`, this step is 1 index read (or N frontmatter reads on fallback), bounded by KB count.
+**One git call, then direct reads — no `.cjs` script.** After resolving `{worktree}`, this step is 1 index read (or N frontmatter reads on fallback), plus one heading listing and one Rules read per selected KB, bounded by KB count.
 
 Use `FEATURE_KNOWLEDGE` **locally** for research framing. Pass to each Research agent in Phase 4.
 
@@ -138,7 +160,7 @@ Generate topic slug from the research question (kebab-case, lowercase, no articl
 
 Only if `codebase` type is in RESEARCH_PLAN.
 
-Spawn `Agent(subagent_type="Skim")` targeting codebase areas relevant to the research question.
+Spawn `Agent(subagent_type="Skim")` with `LEARNING` from the settings line, targeting codebase areas relevant to the research question.
 
 Skip and set ORIENT_OUTPUT = "(none)" if `codebase` type is not in RESEARCH_PLAN.
 
@@ -152,7 +174,7 @@ Spawn 2-5 `Agent(subagent_type="Research")` agents **in a single message** (para
 Each Research agent receives:
 - `RESEARCH_TYPE`, `RESEARCH_QUESTION`, `OUTPUT_PATH` from RESEARCH_PLAN
 - `DECISIONS_CONTEXT`: From Phase 1
-- `FEATURE_KNOWLEDGE`: From Phase 1
+- `FEATURE_KNOWLEDGE`: `{feature_knowledge}` from Phase 1
 - `ORIENT_OUTPUT`: Only for `codebase` type
 - `WORKTREE_PATH`: If in a worktree context
 
@@ -183,7 +205,7 @@ If external research was skipped due to tool unavailability: inform user.
 
 ### Phase 7: Feature Knowledge Creation (Conditional)
 
-**Requires:** RESEARCH_SUMMARY, DECISIONS_CONTEXT
+**Requires:** RESEARCH_SUMMARY
 **Produces:** FEATURE_KNOWLEDGE_STATUS (created | skipped)
 
 1. If `codebase` type was not in RESEARCH_PLAN → skip

package/dist/commands/resolve.md

@@ -24,7 +24,7 @@ Process issues from code review reports: triage every issue through the blast-ra
 
 1. **Discover resolvable worktrees** using the `devflow:worktree-support` skill discovery algorithm:
    - Run `git worktree list --porcelain` → parse, filter (skip protected/detached/mid-rebase), dedup by branch, sort by recent commit
-   - See the `devflow:worktree-support` skill for the full 7-step algorithm and canonical protected branch list
+   - Invoke the `devflow:worktree-support` skill, then Read its `references/discovery.md` from the skill's base directory for the full 7-step algorithm; the canonical protected branch list stays in the skill
    - Additional filter: must have unresolved reviews (latest review directory has no `resolution-summary.md`)
 2. **If `--path` flag provided:** use only that worktree, skip discovery
    **`--path` validation**: Before proceeding, verify the path exists as a directory and appears in `git worktree list` output. If not: report error and stop.
@@ -85,10 +85,22 @@ Set `TARGET_DIR` to the selected review or bug-analysis directory path, and `TAR
 
 #### Step 0d: Load Project Decisions
 
-**Produces:** DECISIONS_CONTEXT, FEATURE_KNOWLEDGE, EVIDENCE_POLICY, ISSUE_REQUIRED, APPLY_CONVENTIONS, REQUIRE_NON_AUTHOR_APPROVAL, REVIEW_PUBLICATION, RESOLUTION_TS
+**Produces:** DECISIONS_CONTEXT, FEATURE_KNOWLEDGE, FEATURE_KNOWLEDGE_RULES, EVIDENCE_POLICY, ISSUE_REQUIRED, APPLY_CONVENTIONS, REQUIRE_NON_AUTHOR_APPROVAL, REVIEW_PUBLICATION, RESOLUTION_TS
+
+**Resolve the settings line** once per worktree root, reusing a line this run already resolved for the same root. `{root}` is the worktree the values are for — the repository root when the run has one worktree:
+
+```bash
+node "$HOME/.devflow/scripts/resolve-settings.cjs" "{root}" 2>/dev/null; echo "exit=$?"
+```
+
+Accept the output only when it is exactly two lines: `exit=0` last and, before it, one line of the form `TRACKER=<github|jira|linear> TRACKER_SOURCE=<project|personal|machine|default> TRACKER_WARN=<none|mismatch|invalid> SITE=<none|https://<host>> KEY=<none|<key>> REVIEW_PUBLICATION=<off|auto|full> COMPLIANCE=<off|generic|<id>[,<id>…]> MEMORY=<on|off> LEARNING=<on|off> KNOWLEDGE=<on|off>` — these fields, in this order, nothing else, where `<host>` is a lowercase dotted host name alone, `<key>` is 2–10 of `A-Z`, `0-9` and `_` starting with a letter, and each `<id>` is one of `gdpr`, `hipaa`, `pci-dss`, `soc2`, `iso-27001`, `sox`. **Anything else** (a non-zero exit, no line, extra text, or a missing, reordered or unlisted field or value) ⇒ use `TRACKER=github TRACKER_SOURCE=default TRACKER_WARN=invalid SITE=none KEY=none REVIEW_PUBLICATION=off COMPLIANCE=generic MEMORY=on LEARNING=on KNOWLEDGE=off` instead.
+
+The accepted line is the only source of these values: the script alone folds the committed `.devflow/project.json`, the personal `.devflow/config.json` and the machine manifest.
 
 ### Load DECISIONS_CONTEXT
 
+When the settings line says `LEARNING=off`, set `DECISIONS_CONTEXT` to `(none)` and skip this step, locating no ledger and reading no index.
+
 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`):
 
 ```bash
@@ -146,22 +158,32 @@ Glob `{worktree}/.devflow/features/*/KNOWLEDGE.md`. For each file found, read on
 
 Match the current task area and description against each index line (or frontmatter `description` + `directories` on fallback). Select entries whose documented area overlaps the current task. This is a relevance judgment — prefer specificity over breadth.
 
-**Step 4 — Read selected KBs:**
+**Step 4 — Read each selected KB's Rules:**
+
+For each selected entry, `{kb}` is `{worktree}/.devflow/features/{slug}/KNOWLEDGE.md`:
+
+1. List its `##` headings with line numbers through Bash: `command grep -n '^## ' "{kb}"`. This only locates sections; the text of a KB comes from the Read view alone.
+2. Read the `## Rules` range (its line to the next heading) with the Read tool, using `offset` and `limit`, and choose the one to three bullets most relevant to the current task. The choice is yours, made per KB.
+3. If the KB has no `## Rules` section, choose one to three entries from its `## Anti-Patterns` or `## Gotchas` range the same way, and label them by that section's name instead of an ID.
 
-For each selected entry, read `{worktree}/.devflow/features/{slug}/KNOWLEDGE.md` in full. When the KB content contradicts the current code you observe, **trust the code** — the code is the freshness mechanism; the KB may lag behind.
+When a KB contradicts the code you observe, **trust the code** — the code is the freshness mechanism; the KB may lag behind. A missing Rules section, a missing heading list and `(none)` are legitimate states, not errors.
 
-**Step 5 — Set FEATURE_KNOWLEDGE:**
+**Step 5 — Set FEATURE_KNOWLEDGE and FEATURE_KNOWLEDGE_RULES:**
 
-Concatenate the selected KNOWLEDGE.md files under slug headers:
+Write one block per selected KB. Paste each bullet verbatim from the Read view, never from a shell view. The path is relative to the checkout root; an agent resolves it under `WORKTREE_PATH` when one is provided.
 
 ```
 --- Feature knowledge: {slug} ---
-{full KNOWLEDGE.md content}
+KB: .devflow/features/{slug}/KNOWLEDGE.md
+Rules:
+- **KB-AP-2** {bullet text, verbatim}
+- **KB-INV-1** {bullet text, verbatim}
+Headings: L5 Rules · L40 Overview · L62 Anti-Patterns · L118 Key Files
 ```
 
-If no KBs exist, no KBs are relevant, or `.devflow/features/` is absent, set `FEATURE_KNOWLEDGE` to `(none)`.
+A KB with no Rules section labels its entries `Rules ({section name}):` and gives them no ID. `FEATURE_KNOWLEDGE` is these blocks; `FEATURE_KNOWLEDGE_RULES` is the same blocks without the `Headings:` line. Both come from this one selection, and each spawn names the variable its recipient takes. If no KBs exist, no KBs are relevant, or `.devflow/features/` is absent, set both to `(none)`.
 
-**One git call, then direct file reads — no `.cjs` script.** After resolving `{worktree}`, this step is 1 index read (or N frontmatter reads on fallback), bounded by KB count.
+**One git call, then direct reads — no `.cjs` script.** After resolving `{worktree}`, this step is 1 index read (or N frontmatter reads on fallback), plus one heading listing and one Rules read per selected KB, bounded by KB count.
 
 Pass `FEATURE_KNOWLEDGE` to the Triage agent in Phase 2.
 
@@ -176,17 +198,7 @@ Accept the output only when it is exactly two lines: `exit=0` last and, before i
 Set `EVIDENCE_POLICY`, `ISSUE_REQUIRED`, `APPLY_CONVENTIONS` and `REQUIRE_NON_AUTHOR_APPROVAL` from the accepted line. Pass agents only the three mechanism inputs, never `EVIDENCE_POLICY`. Report `Evidence policy: {EVIDENCE_POLICY} (source: {SOURCE})`, plus any `WARN` tokens as advisory, once in the final report.
 Reuse this result for every worktree.
 
-**Resolve the settings line** once per worktree root, reusing a line this run already resolved for the same root. `{root}` is the worktree the values are for — the repository root when the run has one worktree:
-
-```bash
-node "$HOME/.devflow/scripts/resolve-settings.cjs" "{root}" 2>/dev/null; echo "exit=$?"
-```
-
-Accept the output only when it is exactly two lines: `exit=0` last and, before it, one line of the form `TRACKER=<github|jira|linear> TRACKER_SOURCE=<project|personal|machine|default> TRACKER_WARN=<none|mismatch|invalid> SITE=<none|https://<host>> KEY=<none|<key>> REVIEW_PUBLICATION=<off|auto|full> COMPLIANCE=<off|generic|<id>[,<id>…]> MEMORY=<on|off> LEARNING=<on|off> KNOWLEDGE=<on|off>` — these fields, in this order, nothing else, where `<host>` is a lowercase dotted host name alone, `<key>` is 2–10 of `A-Z`, `0-9` and `_` starting with a letter, and each `<id>` is one of `gdpr`, `hipaa`, `pci-dss`, `soc2`, `iso-27001`, `sox`. **Anything else** (a non-zero exit, no line, extra text, or a missing, reordered or unlisted field or value) ⇒ use `TRACKER=github TRACKER_SOURCE=default TRACKER_WARN=invalid SITE=none KEY=none REVIEW_PUBLICATION=off COMPLIANCE=generic MEMORY=on LEARNING=on KNOWLEDGE=off` instead.
-
-The accepted line is the only source of these values: the script alone folds the committed `.devflow/project.json`, the personal `.devflow/config.json` and the machine manifest.
-
-**Resolve `REVIEW_PUBLICATION` per worktree:** take `REVIEW_PUBLICATION` from that worktree's settings line, with `{root}` the worktree's root — multi-worktree repos may resolve different values per worktree. The line already caps the personal choice at the team's (D-PUBLICATION-CEILING), so it is `off`, `auto` or `full`, and `off` when the line was unresolvable.
+**Resolve `REVIEW_PUBLICATION` per worktree:** take `REVIEW_PUBLICATION` from that worktree's settings line — the line resolved above for `{root}`, the worktree's root, by the settings block when this run has not yet resolved that root; multi-worktree repos may resolve different values per worktree. The line already caps the personal choice at the team's (D-PUBLICATION-CEILING), so it is `off`, `auto` or `full`, and `off` when the line was unresolvable.
 
 **Evidence stub:** only when `EVIDENCE_POLICY` is `required`, a resolved `off` becomes `stub`, so a counts-only record still reaches the PR. `stub` is never a config value: the settings line never carries it.
 
@@ -302,8 +314,8 @@ For each batch, spawn Code agent with `OPERATION: issue-fix` and `PUSH: false`:
 
 ```
 Agent(subagent_type="Code"):
-"TASK_ID: resolve-{batch-id}
-OPERATION: issue-fix
+"OPERATION: issue-fix
+TASK_ID: resolve-{batch-id}
 ISSUES: {fix_now_issues_in_batch}
 SCOPE: {risk_tier_per_issue}
 PUSH: false
@@ -348,7 +360,8 @@ Agent(subagent_type="Simplify", run_in_background=false):
 "TASK_DESCRIPTION: Issue resolution fixes
 WORKTREE_PATH: {worktree_path}  (omit if cwd)
 FILES_CHANGED: {list of files modified by Code agents}
-Simplify and refine the fixes for clarity and consistency"
+Simplify and refine the fixes for clarity and consistency
+Commit any improvements with a conventional-commit message."
 ```
 
 ### Phase 7: Verification Gate
@@ -376,13 +389,14 @@ Run build, typecheck, lint, test. Report pass/fail with failure details."
    - Spawn Code agent with fix context:
    ```
    Agent(subagent_type="Code"):
-   "TASK_ID: resolve-{batch-id}-valfix-{count}
-   OPERATION: validation-fix
+   "OPERATION: validation-fix
+   TASK_ID: resolve-{batch-id}-valfix-{count}
    VALIDATION_FAILURES: {parsed failures from Validate agent}
    SCOPE: Fix only the listed failures, no other changes
    PUSH: false
    CREATE_PR: false
    WORKTREE_PATH: {worktree_path}  (omit if cwd)
+   DECISIONS_CONTEXT: {decisions_context}
    COMPLIANCE_FRAMEWORKS: {COMPLIANCE_FRAMEWORKS}"
    ```
    - Loop back to re-validate
@@ -415,14 +429,24 @@ If `fork_no_push` is set → skip: "Cannot push to fork — skipping CI validati
 
 Otherwise, for each worktree with fixes:
 
-<!-- PATTERN: ci-status-gate — shared polling/classification/budget logic; context-specific preamble lives outside this block -->
-1. Spawn `Agent(subagent_type="Git")` with `OPERATION: check-ci-status` and `WORKTREE_PATH`.
+`PR_NUMBER` is the worktree's `pr_number` from Phase 0; when it is absent, skip: "No PR/CI configured, skipping CI validation."
+
+**Push first, outside the gate block.** The gate waits on the pushed head, so push once more with the gate's own command — never forced, and no retry:
+
+```bash
+git -C {worktree} push; echo "exit=$?"
+```
+
+Phase 7 has pushed already, so this is a no-op unless the head moved since. `exit=0` continues to the gate. Any other result records `TRACEABILITY: DEGRADED (ci push failed)`, reports "CI status unknown — verify manually before merging" and skips the wait for this worktree. Pass `WORKTREE_PATH: {worktree_path}` on the fix spawn below.
+
+<!-- PATTERN: ci-status-gate -->
+1. Wait: run `cd {worktree} && HEAD_SHA=$(git rev-parse HEAD) && node "$HOME/.devflow/scripts/ci-wait.cjs" --pr {PR_NUMBER} --head "$HEAD_SHA"` through the Bash tool with `timeout: 600000`. Each run is one wait of at most 570 seconds and prints one line, `CI <STATUS> pr=… head=… failing=… pending=… waited=…` (INDETERMINATE adds `reason=…`). A missing or unparseable line, a status outside the six below, or a non-zero exit is INDETERMINATE.
 2. **If PASSING** → proceed to next phase.
 3. **If NO_PR or NO_CI** → skip: "No PR/CI configured, skipping CI validation." Proceed to next phase.
-4. **If PENDING** → poll every 60 seconds (global budget, see step 7). Re-spawn Git agent each poll. If PASSING → proceed. If still PENDING after budget exhausted → report "CI still running — verify manually before merging" and proceed.
-5. **If INDETERMINATE** → poll as PENDING within the same budget. If still INDETERMINATE after budget exhausted → report "CI status unknown — verify manually before merging" and proceed.
-6. **If FAILING** → report failing checks. Spawn `Agent(subagent_type="Code")` with `COMPLIANCE_FRAMEWORKS` to fix CI failures based on check names and failure context. After fix, push and re-check. Max 2 fix attempts. If still failing → report failures and proceed.
-7. **Total budget**: max 10 polls and max 2 fix attempts across all check/fix cycles combined. If the budget is exhausted, report current status and proceed.
+4. **If PENDING** and fewer than 3 waits have run → wait again (step 1). After the third wait → report "CI still running — verify manually before merging" and proceed.
+5. **If INDETERMINATE** and fewer than 3 waits have run → wait again (step 1). After the third wait → report "CI status unknown — verify manually before merging" and proceed.
+6. **If FAILING** and fewer than 2 fixes have run → report the failing checks from the line. Spawn `Agent(subagent_type="Code")` whose prompt opens with `OPERATION: ci-fix`, with `COMPLIANCE_FRAMEWORKS`, `CI_FAILURES`, `DECISIONS_CONTEXT` and `PUSH: false`; `CI_FAILURES` holds the failing-check names from the line and nothing else, because the Code agent fetches the full names and reads the logs itself and this command reads none. After a fix, push with the command above and, if a wait remains, wait again (step 1); a failed push records `TRACEABILITY: DEGRADED (ci push failed)`, reports "CI status unknown — verify manually before merging" and stops waiting. After the second fix still FAILING → report the failing checks and proceed.
+7. **Budget**: at most 3 waits and 2 fixes in all, per worktree. When one is spent, report the current status and proceed.
 <!-- /PATTERN: ci-status-gate -->
 
 ### Phase 9: Manage Debt (Sequential)
@@ -455,7 +479,7 @@ After manage-debt completes:
 
 **Step 9b-0: Re-verify stale test-plan items**
 
-Run this step only when this run's Phase 7 push succeeded — the one way /resolve moves the PR head — and a PR is known; otherwise skip it and Step 9b-3, and record `STALE_REVERIFICATION` as `SKIPPED (head unchanged)`. Detection needs no Git agent: from the worktree root, run the evidence script, which re-derives every test-plan state at the new head and writes the stale TP lines whose text the PR's trusted evidence record vouches for:
+Run this step only when a push of this run succeeded — Phase 7's, or the push of Phase 8's gate — and a PR is known; otherwise skip it and Step 9b-3, and record `STALE_REVERIFICATION` as `SKIPPED (head unchanged)`. Detection needs no Git agent: from the worktree root, run the evidence script, which re-derives every test-plan state at the new head and writes the stale TP lines whose text the PR's trusted evidence record vouches for:
 
 ```bash
 cd {worktree} && node "$HOME/.devflow/scripts/verify-evidence.cjs" verify --pr {pr_number} --stale-out "{TARGET_DIR_REL}/stale-plan.md"; echo "exit=$?"
@@ -607,7 +631,7 @@ Final gate: {PASS | FAILED after N attempts}
 - Resolution comment: {POSTED | POSTED+TRUNCATED | SKIPPED (already posted) | SKIPPED (publication off) | SKIPPED (no PR) | DEGRADED (reason)}
 - Publication: {FULL (private repo) | FULL (config override) | STUB (public repository) | OFF (publication disabled by config) | STUB (visibility undeterminable) | STUB (evidence policy)}
 - Thread replies: {COMPLETE | PARTIAL | TRUNCATED | SKIPPED (reason) | DEGRADED (reason)}
-- Push: {pushed | skipped (no fixes) | skipped (cannot push to fork)}
+- Push: {pushed (Phase 7, a CI-fix push, or both) | skipped (no fixes) | skipped (cannot push to fork) | DEGRADED (ci push failed)}
 - Test-plan re-verification: {Test plan: n stale, m re-verified | SKIPPED (head unchanged) | DEGRADED (reason)}
 - Test-plan evidence: {the EVIDENCE line's VERIFIED-CI + ATTESTED-LOCAL / total, then the Body / Comment line | SKIPPED (reason) | DEGRADED (reason)}
 
@@ -631,24 +655,14 @@ git -C "{start}" rev-parse --show-toplevel
 
 and use its one-line output. If the command fails (outside a git repository), `{worktree}` is the start directory itself. All paths below are relative to `{worktree}`.
 
-**Step 1 — Check the opt-out gate, with `{root}` = `{worktree}`:**
-
-**Resolve the settings line** once per worktree root, reusing a line this run already resolved for the same root. `{root}` is the worktree the values are for — the repository root when the run has one worktree:
-
-```bash
-node "$HOME/.devflow/scripts/resolve-settings.cjs" "{root}" 2>/dev/null; echo "exit=$?"
-```
-
-Accept the output only when it is exactly two lines: `exit=0` last and, before it, one line of the form `TRACKER=<github|jira|linear> TRACKER_SOURCE=<project|personal|machine|default> TRACKER_WARN=<none|mismatch|invalid> SITE=<none|https://<host>> KEY=<none|<key>> REVIEW_PUBLICATION=<off|auto|full> COMPLIANCE=<off|generic|<id>[,<id>…]> MEMORY=<on|off> LEARNING=<on|off> KNOWLEDGE=<on|off>` — these fields, in this order, nothing else, where `<host>` is a lowercase dotted host name alone, `<key>` is 2–10 of `A-Z`, `0-9` and `_` starting with a letter, and each `<id>` is one of `gdpr`, `hipaa`, `pci-dss`, `soc2`, `iso-27001`, `sox`. **Anything else** (a non-zero exit, no line, extra text, or a missing, reordered or unlisted field or value) ⇒ use `TRACKER=github TRACKER_SOURCE=default TRACKER_WARN=invalid SITE=none KEY=none REVIEW_PUBLICATION=off COMPLIANCE=generic MEMORY=on LEARNING=on KNOWLEDGE=off` instead.
-
-The accepted line is the only source of these values: the script alone folds the committed `.devflow/project.json`, the personal `.devflow/config.json` and the machine manifest.
+**Step 1 — Check the opt-out gate, with `{root}` = `{worktree}`:** take the settings line resolved above for that root, resolving it with the settings block when this run has not yet.
 
 If the settings line says `KNOWLEDGE=off`, skip write-back entirely. The machine switch (`devflow knowledge --disable`), the repository and the personal settings can each turn knowledge off, and none can turn it back on (D-FEATURES-NARROW-ONLY). The fail-closed line says `KNOWLEDGE=off` too, so an unresolvable line skips write-back.
 
 **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.
@@ -671,7 +685,7 @@ Write the knowledge base to:
 Then update the index cache by performing a read-modify-write on:
   {worktree}/.devflow/features/index.md
 
-Index line format: `- **{slug}** — {areas} — {Use-when description}`
+Index line format: `- **{slug}** — {areas} — {Use-when description}` — at most 300 characters, the description at most 220; reword a longer one, never cut it.
 
 If the line for this slug already exists in index.md, replace it. If it does not exist, append it. If index.md does not exist, create it with just this line.
 
@@ -718,7 +732,7 @@ When the Knowledge agent reports `KB_COMMIT: skipped (detached HEAD)`, the files
 ├─ Phase 7: Verification Gate [Validate agent, haiku] + push + Code agent validation-fix loop ≤2
 │
 ├─ Phase 8: CI Status Gate (conditional — skipped if no fixes or verification FAILED)
-│  └─ Git agent (check-ci-status) → poll/fix loop
+│  └─ push, then ci-wait.cjs (inline, one wait ≤ 570 s) → Code agent on FAILING (3 waits + 2 fixes per worktree)
 │
 ├─ Phase 9: Git agent (manage-debt) — FIX_SEPARATE + TECH_DEBT → backfill Tracked={ISSUE_REF} (or TRACEABILITY: DEGRADED on failure)
 │  SEQUENTIAL across worktrees