ai-factory 2.3.0 → 2.4.0

package/skills/aif-explore/SKILL.md

@@ -2,18 +2,26 @@
 name: aif-explore
 description: Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
 argument-hint: "[topic or plan name]"
-allowed-tools: Read Glob Grep Bash AskUserQuestion Questions
+allowed-tools: Read Glob Grep Write Edit Bash AskUserQuestion Questions
 disable-model-invocation: true
 ---
 
 Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
 
-**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks to implement something, remind them to exit explore mode first (e.g., start with `/aif-plan`). You MAY update AI Factory context files (DESCRIPTION.md, ARCHITECTURE.md, RULES.md) if the user asks—that's capturing thinking, not implementing.
+**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER implement features or modify project code. If the user asks to implement something, remind them to exit explore mode first (e.g., start with `/aif-plan`). If the user asks to persist exploration context, write/edit **only** `.ai-factory/RESEARCH.md` (this is capturing thinking, not implementing).
 
 **This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
 
 ---
 
+## Artifact Ownership
+
+- Primary ownership in explore mode: `.ai-factory/RESEARCH.md` only.
+- All other context artifacts (`DESCRIPTION.md`, `ARCHITECTURE.md`, `ROADMAP.md`, `RULES.md`, plan files) are read-only in this mode.
+- If a discovery should affect another artifact, capture it in RESEARCH now and route follow-up to the owner command later.
+
+---
+
 ## The Stance
 
 - **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
@@ -76,6 +84,26 @@ Depending on what the user brings, you might:
 
 You have access to AI Factory's project context. Use it naturally, don't force it.
 
+**Read `.ai-factory/skill-context/aif-explore/SKILL.md`** — MANDATORY if the file exists.
+
+This file contains project-specific rules accumulated by `/aif-evolve` from patches,
+codebase conventions, and tech-stack analysis. These rules are tailored to the current project.
+
+**How to apply skill-context rules:**
+- Treat them as **project-level overrides** for this skill's general instructions
+- When a skill-context rule conflicts with a general rule written in this SKILL.md,
+  **the skill-context rule wins** (more specific context takes priority — same principle as nested CLAUDE.md files)
+- When there is no conflict, apply both: general rules from SKILL.md + project rules from skill-context
+- Do NOT ignore skill-context rules even if they seem to contradict this skill's defaults —
+  they exist because the project's experience proved the default insufficient
+- **CRITICAL:** skill-context rules apply to ALL outputs of this skill — including exploration
+  summaries, diagrams, and any file updates (DESCRIPTION.md, ARCHITECTURE.md). If a skill-context
+  rule says "exploration MUST cover X" or "summary MUST include Y" — you MUST comply. Producing
+  output that ignores skill-context rules is a bug.
+
+**Enforcement:** After generating any output artifact, verify it against all skill-context rules.
+If any rule is violated — fix the output before presenting it to the user.
+
 ### Check for context
 
 At the start, read these files if present:
@@ -83,6 +111,7 @@ At the start, read these files if present:
 - `.ai-factory/DESCRIPTION.md` — project description, tech stack, constraints
 - `.ai-factory/ARCHITECTURE.md` — architecture decisions, folder structure
 - `.ai-factory/RULES.md` — project conventions and rules
+- `.ai-factory/RESEARCH.md` — persisted exploration notes (so you can `/clear` and still keep context)
 - `.ai-factory/PLAN.md` — active fast plan (if any)
 - `.ai-factory/plans/<branch>.md` — active full plans (if any)
 - `.ai-factory/ROADMAP.md` — strategic milestones (if any)
@@ -91,6 +120,7 @@ This tells you:
 - What the project is about
 - What conventions to follow
 - If there's active work in progress
+- Any prior exploration context worth carrying into planning
 
 ### Input handling
 
@@ -122,22 +152,81 @@ If the user mentions a plan or you detect one is relevant:
 
 3. **Offer to capture when decisions are made**
 
-   | Insight Type | Where to Capture |
-   |--------------|------------------|
-   | New requirement | `.ai-factory/DESCRIPTION.md` (stack section) |
-   | Architecture decision | `.ai-factory/ARCHITECTURE.md` |
-   | Project convention | `.ai-factory/RULES.md` |
-   | New task/feature | Run `/aif-plan` to create plan |
-   | Strategic direction | `.ai-factory/ROADMAP.md` |
-   | Assumption invalidated | Relevant file |
+   Default in explore mode: capture everything in `.ai-factory/RESEARCH.md` so it survives `/clear`.
+   Later (during planning), you can migrate stabilized decisions into the appropriate context file.
+
+   | Insight Type | Capture Now (Explore) | Later (Optional) |
+   |--------------|------------------------|------------------|
+   | New requirement | `.ai-factory/RESEARCH.md` | `.ai-factory/DESCRIPTION.md` |
+   | Architecture decision | `.ai-factory/RESEARCH.md` | `.ai-factory/ARCHITECTURE.md` |
+   | Project convention | `.ai-factory/RESEARCH.md` | `.ai-factory/RULES.md` |
+   | Strategic direction | `.ai-factory/RESEARCH.md` | `.ai-factory/ROADMAP.md` |
+   | Assumption invalidated | `.ai-factory/RESEARCH.md` | Relevant file |
+   | Exploration context (persisted) | `.ai-factory/RESEARCH.md` | (keep in RESEARCH) |
+   | New task/feature | Run `/aif-plan` | `.ai-factory/PLAN.md` or `.ai-factory/plans/<branch>.md` |
 
    Example offers:
-   - "That's an architecture decision. Add it to ARCHITECTURE.md?"
-   - "This is a new convention. Add it to RULES.md?"
-   - "This changes the plan. Update the plan file?"
+   - "Want me to save this to `.ai-factory/RESEARCH.md` so you can `/clear` and come back later?"
+   - "That's an architecture decision — save it to RESEARCH now and we can migrate it to ARCHITECTURE during planning."
 
 4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
 
+### Optional: Persist exploration context (`.ai-factory/RESEARCH.md`)
+
+If the conversation is crystallizing (you're about to plan, you want to `/clear`, or you want to continue later), offer to save a compact, durable research snapshot.
+
+**Hard rule in explore mode:** If the user chooses to save, you may write/edit **only** `.ai-factory/RESEARCH.md` (and create the `.ai-factory/` directory if missing). Do not write or modify any other project files.
+
+Ask:
+
+```
+Save these exploration results to .ai-factory/RESEARCH.md so we can /clear and /aif-plan can reuse them?
+
+Options:
+1. Yes — update Active Summary + append a new Session (recommended)
+2. Yes — update Active Summary only
+3. No
+```
+
+If user selects (1) or (2):
+- Ensure `.ai-factory/` exists (`mkdir -p .ai-factory`)
+- If `.ai-factory/RESEARCH.md` does not exist, create it with this skeleton:
+
+```markdown
+# Research
+
+Updated: YYYY-MM-DD HH:MM
+Status: active
+
+## Active Summary (input for /aif-plan)
+<!-- aif:active-summary:start -->
+Topic:
+Goal:
+Constraints:
+Decisions:
+Open questions:
+Success signals:
+Next step:
+<!-- aif:active-summary:end -->
+
+## Sessions
+<!-- aif:sessions:start -->
+<!-- aif:sessions:end -->
+```
+
+- Update the `Updated:` timestamp
+- Replace only the content inside `aif:active-summary:start/end`
+- If user selected option (1), append a new session entry just before `<!-- aif:sessions:end -->`:
+
+```markdown
+### YYYY-MM-DD HH:MM — <short title>
+What changed:
+Key notes:
+Links (paths):
+```
+
+Keep prior sessions verbatim (do not rewrite history).
+
 ---
 
 ## What You Don't Have To Do

package/skills/aif-fix/SKILL.md

@@ -48,6 +48,26 @@ Fix a specific bug or problem in the codebase. Supports two modes: immediate fix
 - If the current problem resembles a past patch — apply the same approach or avoid the same mistakes
 - This is your accumulated experience. Use it.
 
+**Read `.ai-factory/skill-context/aif-fix/SKILL.md`** — MANDATORY if the file exists.
+
+This file contains project-specific rules accumulated by `/aif-evolve` from patches,
+codebase conventions, and tech-stack analysis. These rules are tailored to the current project.
+
+**How to apply skill-context rules:**
+- Treat them as **project-level overrides** for this skill's general instructions
+- When a skill-context rule conflicts with a general rule written in this SKILL.md,
+  **the skill-context rule wins** (more specific context takes priority — same principle as nested CLAUDE.md files)
+- When there is no conflict, apply both: general rules from SKILL.md + project rules from skill-context
+- Do NOT ignore skill-context rules even if they seem to contradict this skill's defaults —
+  they exist because the project's experience proved the default insufficient
+- **CRITICAL:** skill-context rules apply to ALL outputs of this skill — including the FIX_PLAN.md
+  template and patch files. The FIX_PLAN.md template in Step 1.1 is a **base structure**. If a
+  skill-context rule says "steps MUST include X" or "plan MUST have section Y" — you MUST augment
+  the template accordingly. Generating a FIX_PLAN.md or patch that violates skill-context rules is a bug.
+
+**Enforcement:** After generating any output artifact, verify it against all skill-context rules.
+If any rule is violated — fix the output before presenting it to the user.
+
 ### Step 1: Understand the Problem & Choose Mode
 
 From `$ARGUMENTS`, identify:
@@ -324,6 +344,8 @@ function fixedFunction(input) {
 8. **Minimal changes** - Don't refactor unrelated code
 9. **One fix at a time** - Don't scope creep
 10. **Clean up** - Delete FIX_PLAN.md after successful fix execution
+11. **Ownership boundary** - `/aif-fix` owns `.ai-factory/FIX_PLAN.md` and `.ai-factory/patches/*.md`; treat `.ai-factory/DESCRIPTION.md`, roadmap/rules/architecture context artifacts as read-only unless the user explicitly requests otherwise
+12. **Logging scope** - Keep `[FIX]` logging requirements for fixes; context-gate outputs in this command should use `WARN`/`ERROR` and must not change global logging policy in other skills
 
 ## After Fixing
 

package/skills/aif-grounded/SKILL.md

@@ -24,6 +24,28 @@ Use when:
 
 ## Workflow
 
+### Step 0: Load Skill Context
+
+**Read `.ai-factory/skill-context/aif-grounded/SKILL.md`** — MANDATORY if the file exists.
+
+This file contains project-specific rules accumulated by `/aif-evolve` from patches,
+codebase conventions, and tech-stack analysis. These rules are tailored to the current project.
+
+**How to apply skill-context rules:**
+- Treat them as **project-level overrides** for this skill's general instructions
+- When a skill-context rule conflicts with a general rule written in this SKILL.md,
+  **the skill-context rule wins** (more specific context takes priority — same principle as nested CLAUDE.md files)
+- When there is no conflict, apply both: general rules from SKILL.md + project rules from skill-context
+- Do NOT ignore skill-context rules even if they seem to contradict this skill's defaults —
+  they exist because the project's experience proved the default insufficient
+- **CRITICAL:** skill-context rules apply to ALL outputs of this skill — including the response
+  format, evidence requirements, and confidence assessment. If a skill-context rule says "analysis
+  MUST include X" or "confidence MUST account for Y" — you MUST comply. Producing an analysis
+  that ignores skill-context rules is a bug.
+
+**Enforcement:** After generating any output artifact, verify it against all skill-context rules.
+If any rule is violated — fix the output before presenting it to the user.
+
 ### Step 1: Classify the request
 
 Classify into one of:

package/skills/aif-implement/SKILL.md

@@ -115,6 +115,26 @@ Based on choice:
 - Apply proper error handling and logging as specified
 - **Avoid pitfalls documented in patches** — don't repeat past mistakes
 
+**Read `.ai-factory/skill-context/aif-implement/SKILL.md`** — MANDATORY if the file exists.
+
+This file contains project-specific rules accumulated by `/aif-evolve` from patches,
+codebase conventions, and tech-stack analysis. These rules are tailored to the current project.
+
+**How to apply skill-context rules:**
+- Treat them as **project-level overrides** for this skill's general instructions
+- When a skill-context rule conflicts with a general rule written in this SKILL.md,
+  **the skill-context rule wins** (more specific context takes priority — same principle as nested CLAUDE.md files)
+- When there is no conflict, apply both: general rules from SKILL.md + project rules from skill-context
+- Do NOT ignore skill-context rules even if they seem to contradict this skill's defaults —
+  they exist because the project's experience proved the default insufficient
+- **CRITICAL:** skill-context rules apply to ALL outputs of this skill — including the code
+  you write and how you update plan checkboxes. If a skill-context rule says "code MUST follow X"
+  or "implementation MUST include Y" — you MUST comply. Writing code that violates skill-context
+  rules is a bug.
+
+**Enforcement:** After generating any output artifact, verify it against all skill-context rules.
+If any rule is violated — fix the output before presenting it to the user.
+
 ### Step 0.1: Find Plan File
 
 **Check for plan files in this order:**
@@ -302,10 +322,44 @@ What's next?
 
 If `.ai-factory/ROADMAP.md` exists:
 1. Read it
+1.1. If the plan file includes `## Roadmap Linkage` with a non-`none` milestone, prefer that milestone for completion marking
 2. Check if the completed work corresponds to any unchecked milestone
 3. If yes — mark it `[x]` and add entry to the Completed table with today's date
 4. Tell the user which milestone was marked done
 
+### Context Maintenance (Artifacts)
+
+Only do this step when there is something concrete to capture.
+
+**DESCRIPTION.md (allowed in this command):**
+- If this plan introduced new dependencies/integrations or changed the stack, update `.ai-factory/DESCRIPTION.md` with factual deltas only.
+- Do not rewrite unrelated sections.
+
+**ARCHITECTURE.md + AGENTS.md (allowed in this command):**
+- If new modules/layers/folders were added (or dependency rules changed), update `.ai-factory/ARCHITECTURE.md` to reflect the new structure and constraints.
+- If you maintain `AGENTS.md` structure maps or entry points, refresh them only when they are now incorrect.
+
+**ROADMAP.md (allowed, limited):**
+- This command may mark milestone completion when evidence is clear.
+- If milestone mapping is ambiguous, emit `WARN [roadmap] ...` and suggest the owner command:
+  - `/aif-roadmap check`
+  - or `/aif-roadmap <short update request>`
+
+**RULES.md (NOT allowed in this command):**
+- Never edit `.ai-factory/RULES.md` from `/aif-implement`.
+- If you discovered repeatable conventions/pitfalls during implementation, propose up to 3 candidate rules and ask the user to add them via `/aif-rules`.
+- Do not invoke `/aif-rules` automatically (it is user-invoked).
+
+If candidate rules exist:
+
+```
+AskUserQuestion: Capture new project rules in `.ai-factory/RULES.md`?
+
+Options:
+1. Yes — output `/aif-rules ...` commands (recommended)
+2. No — skip
+```
+
 ### Context Cleanup
 
 Context is heavy after implementation. All code changes are saved — suggest freeing space:
@@ -477,6 +531,13 @@ Shows progress without executing.
 - ❌ Mark incomplete tasks as done
 - ❌ Violate `.ai-factory/ARCHITECTURE.md` conventions for file placement and module boundaries
 
+## Artifact Ownership Boundaries
+
+- Primary ownership in this command: task execution state and plan progress checkboxes.
+- Allowed context artifact updates: `.ai-factory/DESCRIPTION.md`, `.ai-factory/ARCHITECTURE.md`, and roadmap milestone completion in `.ai-factory/ROADMAP.md` when implementation evidence justifies it.
+- Read-only context in this command by default: `.ai-factory/RULES.md`, `.ai-factory/RESEARCH.md`.
+- Context-gate findings should be communicated as `WARN`/`ERROR` outputs only; this does not replace the required verbose implementation logging rules below.
+
 For progress display format, blocker handling, session continuity examples, and full flow examples → see `references/IMPLEMENTATION-GUIDE.md`
 
 ## Critical Rules

package/skills/aif-improve/SKILL.md

@@ -79,6 +79,26 @@ If patches exist, read them to understand:
 - What patterns to avoid
 - What the plan should account for
 
+**Read `.ai-factory/skill-context/aif-improve/SKILL.md`** — MANDATORY if the file exists.
+
+This file contains project-specific rules accumulated by `/aif-evolve` from patches,
+codebase conventions, and tech-stack analysis. These rules are tailored to the current project.
+
+**How to apply skill-context rules:**
+- Treat them as **project-level overrides** for this skill's general instructions
+- When a skill-context rule conflicts with a general rule written in this SKILL.md,
+  **the skill-context rule wins** (more specific context takes priority — same principle as nested CLAUDE.md files)
+- When there is no conflict, apply both: general rules from SKILL.md + project rules from skill-context
+- Do NOT ignore skill-context rules even if they seem to contradict this skill's defaults —
+  they exist because the project's experience proved the default insufficient
+- **CRITICAL:** skill-context rules apply to ALL outputs of this skill — including the Plan
+  Refinement Report and any plan modifications. If a skill-context rule says "tasks MUST include X"
+  or "plan structure MUST have Y" — you MUST apply these when refining. Generating a refinement
+  report that ignores skill-context rules is a bug.
+
+**Enforcement:** After generating any output artifact, verify it against all skill-context rules.
+If any rule is violated — fix the output before presenting it to the user.
+
 **1.4: Load current task list**
 
 ```

package/skills/aif-loop/SKILL.md

@@ -93,6 +93,26 @@ Read these files if present:
 
 Use them to keep outputs aligned with project conventions.
 
+**Read `.ai-factory/skill-context/aif-loop/SKILL.md`** — MANDATORY if the file exists.
+
+This file contains project-specific rules accumulated by `/aif-evolve` from patches,
+codebase conventions, and tech-stack analysis. These rules are tailored to the current project.
+
+**How to apply skill-context rules:**
+- Treat them as **project-level overrides** for this skill's general instructions
+- When a skill-context rule conflicts with a general rule written in this SKILL.md,
+  **the skill-context rule wins** (more specific context takes priority — same principle as nested CLAUDE.md files)
+- When there is no conflict, apply both: general rules from SKILL.md + project rules from skill-context
+- Do NOT ignore skill-context rules even if they seem to contradict this skill's defaults —
+  they exist because the project's experience proved the default insufficient
+- **CRITICAL:** skill-context rules apply to ALL outputs of this skill — including the generated
+  artifact, run state, and evaluation criteria. If a skill-context rule says "artifact MUST include X"
+  or "evaluation MUST check Y" — you MUST comply. Producing loop outputs that violate skill-context
+  rules is a bug.
+
+**Enforcement:** After generating any output artifact, verify it against all skill-context rules.
+If any rule is violated — fix the output before presenting it to the user.
+
 ## Step 0.1: Handle Non-Iteration Commands
 
 If command is `status`, `stop`, `list`, `history`, or `clean`, execute and stop:

package/skills/aif-plan/SKILL.md

@@ -34,6 +34,36 @@ Use this context when:
 - Planning file structure (follow project conventions)
 - **Follow architecture guidelines from `.ai-factory/ARCHITECTURE.md` when planning file structure and task organization**
 
+**Read `.ai-factory/skill-context/aif-plan/SKILL.md`** — MANDATORY if the file exists.
+
+This file contains project-specific rules accumulated by `/aif-evolve` from patches,
+codebase conventions, and tech-stack analysis. These rules are tailored to the current project.
+
+**How to apply skill-context rules:**
+- Treat them as **project-level overrides** for this skill's general instructions
+- When a skill-context rule conflicts with a general rule written in this SKILL.md,
+  **the skill-context rule wins** (more specific context takes priority — same principle as nested CLAUDE.md files)
+- When there is no conflict, apply both: general rules from SKILL.md + project rules from skill-context
+- Do NOT ignore skill-context rules even if they seem to contradict this skill's defaults —
+  they exist because the project's experience proved the default insufficient
+- **CRITICAL:** skill-context rules apply to ALL outputs of this skill — including the PLAN.md
+  template and task format. The plan template from TASK-FORMAT.md is a **base structure**. If a
+  skill-context rule says "tasks MUST include X" or "plan MUST have section Y" — you MUST augment
+  the template accordingly. Generating a plan that violates skill-context rules is a bug.
+
+**Enforcement:** After generating any output artifact, verify it against all skill-context rules.
+If any rule is violated — fix the output before presenting it to the user.
+
+**OPTIONAL (recommended):** Read `.ai-factory/ROADMAP.md` if it exists:
+- Use it to link this plan to a specific milestone (when applicable)
+- This reduces ambiguity in `/aif-implement` milestone completion and `/aif-verify` roadmap gates
+
+**OPTIONAL (recommended):** Read `.ai-factory/RESEARCH.md` if it exists:
+- Treat `## Active Summary (input for /aif-plan)` as an additional requirements source
+- Carry over constraints/decisions into tasks and plan settings
+- Prefer the summary over raw notes; use `## Sessions` only when you need deeper rationale
+- If the user omitted the feature description, use `Active Summary -> Topic:` as the default description
+
 ### Step 0.1: Ensure Git Repository
 
 ```bash
@@ -57,6 +87,10 @@ full        → Full mode (first word)
 - Remaining text becomes the description
 - `--list` and `--cleanup` execute immediately and **STOP** (do NOT continue to Step 1+)
 
+**If the description is empty:**
+- If `.ai-factory/RESEARCH.md` exists and its `Active Summary` has a non-empty `Topic:`, default the description to that topic (no extra user input required)
+- Otherwise, ask the user for a short feature description
+
 **If `--list` is present**, jump to [--list Subcommand](#--list-subcommand).
 **If `--cleanup` is present**, jump to [--cleanup Subcommand](#--cleanup-subcommand).
 
@@ -73,6 +107,10 @@ Options:
 2. Fast — quick plan, no branch, saves to PLAN.md
 ```
 
+If the user did not provide a description and `.ai-factory/RESEARCH.md` exists:
+- Mention that you will default the description to the `Active Summary` topic
+- Only ask for `full` vs `fast` (no description prompt needed)
+
 For concrete parsing examples and expected behavior per command shape, read `references/EXAMPLES.md` (Argument Parsing).
 
 ---
@@ -140,7 +178,11 @@ AskUserQuestion: Before we start, a few questions:
    - [ ] Yes, update docs (/aif-docs)
    - [ ] No, skip docs
 
-4. Any specific requirements or constraints?
+4. Roadmap milestone linkage (only if `.ai-factory/ROADMAP.md` exists):
+   - [ ] Link this plan to a milestone
+   - [ ] Skip — no linkage (allowed; `/aif-verify --strict` should report WARN, not fail, for missing linkage alone)
+
+5. Any specific requirements or constraints?
 ```
 
 **Default to verbose logging.** AI-generated code benefits greatly from extensive logging because:
@@ -150,6 +192,11 @@ AskUserQuestion: Before we start, a few questions:
 
 Store all preferences — they will be used in the plan file and passed to `/aif-implement`.
 
+**If `.ai-factory/ROADMAP.md` exists and the user chose milestone linkage:**
+- Read `.ai-factory/ROADMAP.md` and list candidate milestones (prefer unchecked items)
+- Ask the user to pick one milestone (or type a custom one)
+- Store the selected milestone name and a 1-sentence rationale for inclusion in the plan file
+
 ### Step 1.4: Create Branch or Worktree
 
 **If `--parallel` flag is set → create worktree:**
@@ -179,6 +226,7 @@ WORKTREE="../${DIRNAME}-<branch-name-with-hyphens>"
 # Project context
 cp .ai-factory/DESCRIPTION.md "${WORKTREE}/.ai-factory/DESCRIPTION.md" 2>/dev/null
 cp .ai-factory/ARCHITECTURE.md "${WORKTREE}/.ai-factory/ARCHITECTURE.md" 2>/dev/null
+cp .ai-factory/RESEARCH.md "${WORKTREE}/.ai-factory/RESEARCH.md" 2>/dev/null
 
 # Past lessons / patches
 cp -r .ai-factory/patches/ "${WORKTREE}/.ai-factory/patches/" 2>/dev/null
@@ -242,6 +290,10 @@ AskUserQuestion: Before we start:
    - [ ] No, skip tests
 
 2. Any specific requirements or constraints?
+
+3. Roadmap milestone linkage (only if `.ai-factory/ROADMAP.md` exists):
+   - [ ] Link this plan to a milestone
+   - [ ] Skip — no linkage (allowed; `/aif-verify --strict` should report WARN, not fail, for missing linkage alone)
 ```
 
 **Plan file:** Always `.ai-factory/PLAN.md` (no branch, no branch-named file).
@@ -330,9 +382,19 @@ mkdir -p .ai-factory/plans  # only when saving to branch-named plan files
 - Title with feature name
 - Branch and creation date
 - `Settings` section (Testing, Logging, Docs)
+- `Roadmap Linkage` section (optional, only if `.ai-factory/ROADMAP.md` exists)
+- `Research Context` section (optional, if `.ai-factory/RESEARCH.md` exists)
 - `Tasks` section grouped by phases
 - `Commit Plan` section when there are 5+ tasks
 
+If `.ai-factory/ROADMAP.md` exists:
+- If the user linked a milestone, write `## Roadmap Linkage` with `Milestone: "..."` and `Rationale: ...`
+- If the user skipped linkage, write `## Roadmap Linkage` with `Milestone: "none"` and `Rationale: "Skipped by user"`
+
+If `.ai-factory/RESEARCH.md` exists:
+- Include `## Research Context` by copying only the `Active Summary` (do not paste full `Sessions`)
+- Keep it compact; it should be readable as a one-screen requirements snapshot
+
 Use the canonical template in `references/TASK-FORMAT.md` (Plan File Template).
 
 **Commit Plan Rules:**
@@ -466,6 +528,8 @@ Use canonical examples in `references/TASK-FORMAT.md`:
 6. **Include file paths** — Help implementer know where to work
 7. **Commit checkpoints for large plans** — 5+ tasks need commit plan with checkpoints every 3-5 tasks
 8. **Plan file location** — Fast mode: `.ai-factory/PLAN.md`. Full mode: `.ai-factory/plans/<branch-name>.md`
+9. **Ownership boundary** — This command owns plan files only (`.ai-factory/PLAN.md`, `.ai-factory/plans/<branch>.md`). Use owner commands (`/aif-roadmap`, `/aif-rules`, `/aif-explore`) for their artifacts.
+10. **Roadmap linkage (when available)** — If `.ai-factory/ROADMAP.md` exists, include a `## Roadmap Linkage` section in the plan (or explicitly state it was skipped).
 
 ## Plan File Handling
 

package/skills/aif-plan/references/EXAMPLES.md

@@ -16,6 +16,14 @@
 -> mode=full, description="Add user authentication with OAuth"
 ```
 
+### Full mode with description omitted (defaults from RESEARCH.md)
+
+```text
+/aif-plan full
+-> mode=full
+-> description defaults to .ai-factory/RESEARCH.md Active Summary Topic (if present)
+```
+
 ### Full mode with parallel worktree
 
 ```text
@@ -44,6 +52,14 @@
 -> ask mode interactively, description="Add user authentication"
 ```
 
+### No mode + no description (defaults from RESEARCH.md)
+
+```text
+/aif-plan
+-> ask mode interactively
+-> description defaults to .ai-factory/RESEARCH.md Active Summary Topic (if present)
+```
+
 ## Flow Scenarios
 
 ### Scenario 1: Fast mode
@@ -67,6 +83,7 @@
 -> mode=full
 -> Quick reconnaissance
 -> Branch: feature/user-authentication
+-> If ROADMAP.md exists: asks about milestone linkage, user picks one (or skips)
 -> Asks about tests (Yes), logging (Verbose), docs (Yes)
 -> Creates branch
 -> Explores codebase deeply
@@ -83,6 +100,7 @@
 -> mode=full, parallel=true
 -> Quick reconnaissance
 -> Branch: feature/stripe-checkout
+-> If ROADMAP.md exists: asks about milestone linkage, user picks one (or skips)
 -> Asks about tests (No), logging (Verbose), docs (No)
 -> Creates worktree ../my-project-feature-stripe-checkout
 -> Copies context files, cd into worktree

package/skills/aif-plan/references/TASK-FORMAT.md

@@ -13,6 +13,20 @@ Created: [date]
 - Logging: verbose/standard/minimal
 - Docs: yes/no
 
+## Roadmap Linkage (optional)
+<!-- Only when .ai-factory/ROADMAP.md exists -->
+Milestone: "[milestone name from ROADMAP.md]"  # or "none"
+Rationale: [1 short sentence]
+
+## Research Context (optional)
+<!-- If .ai-factory/RESEARCH.md exists, copy/paste the Active Summary here -->
+Source: .ai-factory/RESEARCH.md (Active Summary)
+
+Goal:
+Constraints:
+Decisions:
+Open questions:
+
 ## Commit Plan
 <!-- For plans with 5+ tasks, define commit checkpoints -->
 - **Commit 1** (after tasks 1-3): "feat: add base models and types"

package/skills/aif-review/SKILL.md

@@ -24,6 +24,42 @@ Perform thorough code reviews focusing on correctness, security, performance, an
 2. Use `gh pr diff <number>` to get the diff
 3. Review all changes in the PR
 
+## Context Gates (Read-Only)
+
+Before finalizing review findings, run read-only context gates:
+
+- Check `.ai-factory/ARCHITECTURE.md` (if present) for boundary/dependency alignment issues.
+- Check `.ai-factory/RULES.md` (if present) for explicit convention violations.
+- Check `.ai-factory/ROADMAP.md` (if present) for milestone alignment and mention missing linkage for likely `feat`/`fix`/`perf` work.
+
+Gate result severity:
+- `WARN` for non-blocking inconsistencies or missing optional files.
+- `ERROR` only for explicit blocking criteria requested by the user/review policy.
+
+`/aif-review` is read-only for context artifacts by default. Do not modify context files unless user explicitly asks.
+
+### Project Context
+
+**Read `.ai-factory/skill-context/aif-review/SKILL.md`** — MANDATORY if the file exists.
+
+This file contains project-specific rules accumulated by `/aif-evolve` from patches,
+codebase conventions, and tech-stack analysis. These rules are tailored to the current project.
+
+**How to apply skill-context rules:**
+- Treat them as **project-level overrides** for this skill's general instructions
+- When a skill-context rule conflicts with a general rule written in this SKILL.md,
+  **the skill-context rule wins** (more specific context takes priority — same principle as nested CLAUDE.md files)
+- When there is no conflict, apply both: general rules from SKILL.md + project rules from skill-context
+- Do NOT ignore skill-context rules even if they seem to contradict this skill's defaults —
+  they exist because the project's experience proved the default insufficient
+- **CRITICAL:** skill-context rules apply to ALL outputs of this skill — including the review
+  summary format and the checklist criteria. If a skill-context rule says "review MUST check X"
+  or "summary MUST include section Y" — you MUST augment the output accordingly. Producing a
+  review that ignores skill-context rules is a bug.
+
+**Enforcement:** After generating any output artifact, verify it against all skill-context rules.
+If any rule is violated — fix the output before presenting it to the user.
+
 ## Review Checklist
 
 ### Correctness
@@ -71,6 +107,9 @@ Perform thorough code reviews focusing on correctness, security, performance, an
 **Files Reviewed:** [count]
 **Risk Level:** 🟢 Low / 🟡 Medium / 🔴 High
 
+### Context Gates
+[Architecture / Rules / Roadmap gate results with WARN/ERROR labels]
+
 ### Critical Issues
 [Must be fixed before merge]
 

package/skills/aif-roadmap/SKILL.md

@@ -23,6 +23,26 @@ Create and maintain a high-level project roadmap with major milestones.
 - Chosen architecture pattern and folder structure
 - Module boundaries and communication patterns
 
+**Read `.ai-factory/skill-context/aif-roadmap/SKILL.md`** — MANDATORY if the file exists.
+
+This file contains project-specific rules accumulated by `/aif-evolve` from patches,
+codebase conventions, and tech-stack analysis. These rules are tailored to the current project.
+
+**How to apply skill-context rules:**
+- Treat them as **project-level overrides** for this skill's general instructions
+- When a skill-context rule conflicts with a general rule written in this SKILL.md,
+  **the skill-context rule wins** (more specific context takes priority — same principle as nested CLAUDE.md files)
+- When there is no conflict, apply both: general rules from SKILL.md + project rules from skill-context
+- Do NOT ignore skill-context rules even if they seem to contradict this skill's defaults —
+  they exist because the project's experience proved the default insufficient
+- **CRITICAL:** skill-context rules apply to ALL outputs of this skill — including the ROADMAP.md
+  template. The template in this SKILL.md is a **base structure**. If a skill-context rule says
+  "roadmap MUST include X" or "milestones MUST have Y" — you MUST augment the template accordingly.
+  Generating a roadmap that violates skill-context rules is a bug.
+
+**Enforcement:** After generating any output artifact, verify it against all skill-context rules.
+If any rule is violated — fix the output before presenting it to the user.
+
 ### Step 1: Determine Mode
 
 If argument is `check` → Mode 3: Check Progress (requires ROADMAP.md)
@@ -271,3 +291,4 @@ Next up: **Milestone Name**
 3. **Never remove milestones silently** — always confirm with user before removing
 4. **Completed table tracks history** — every checked milestone gets a date entry
 5. **NO implementation** — this skill only plans, use `/aif-plan` to start a feature and `/aif-implement` to execute
+6. **Ownership boundary** — this command owns roadmap structure/content; `/aif-implement` may only mark milestones completed when implementation evidence is clear