cfsa-antigravity 2.18.4 → 2.18.5

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "cfsa-antigravity",
-  "version": "2.18.4",
+  "version": "2.18.5",
   "description": "CFSA Pipeline — Constraint-First Specification Architecture for AI agents. Production-grade from line one.",
   "scripts": {
     "changeset": "changeset",

package/template/.agent/kit-sync.md

@@ -1,6 +1,6 @@
 # Kit Sync State
 
 upstream: https://github.com/RepairYourTech/cfsa-antigravity
-last_synced_commit: cef05f046caf3eda65a8bb10c8ce1fd5c457e4c6
-last_synced_at: 2026-03-26T15:01:38Z
-kit_version: 2.18.4
+last_synced_commit: 0f3e0c17f1071bb01866336b115aae77704796f8
+last_synced_at: 2026-03-27T04:02:24Z
+kit_version: 2.18.5

package/template/.agent/skills/session-continuity/protocols/08-spec-pipeline-update.md

@@ -41,3 +41,15 @@
    ```
 
 5. **Report status** — log what was completed and what's next.
+
+6. **Read-back verification** — immediately after updating the tracker:
+
+   (a) Read `.agent/progress/spec-pipeline.md` back.
+   (b) Locate the row for the shard that was just updated.
+   (c) Verify the column that was just marked shows `complete` (not `not-started`, not unchanged, not any other value).
+   (d) If the cell does NOT show `complete`:
+       - Log: `"Pipeline tracker write-back failed for shard [NN] [layer] column — cell still shows [current value]"`
+       - Retry the write once.
+       - Read back and re-verify.
+       - If second attempt fails → **STOP**: `"Unable to update spec-pipeline.md for shard [NN] [layer] after 2 attempts. Do not proceed — investigate before continuing."`
+   (e) On success: log `"Pipeline tracker verified: shard [NN] [layer] = complete"`

package/template/.agent/workflows/write-architecture-spec-deepen.md

@@ -149,7 +149,7 @@ Read `.agent/skills/session-continuity/protocols/ambiguity-gates.md` and run the
 
 ## 13.5. Completion Gate (MANDATORY)
 
-1. Update `.agent/progress/spec-pipeline.md` — mark IA column for this shard as complete
+1. **Verify pipeline tracker** — Read `.agent/progress/spec-pipeline.md` and confirm the IA column for this shard shows `complete`. If it does not → **STOP**: "Pipeline tracker was not updated in Step 11. Go back and run Protocol 08 now before proceeding."
 2. Scan this conversation for memory-capture triggers (see rule: `memory-capture`):
    - Patterns observed → write to `memory/patterns.md`
    - Non-trivial decisions made → write to `memory/decisions.md`

package/template/.agent/workflows/write-architecture-spec-design.md

@@ -22,7 +22,19 @@ Explore requirements, map all interactions, and define contracts, data models, a
 
 **Prerequisite**: Skeleton IA shard must exist in `docs/plans/ia/`. If it does not, tell the user to run `/decompose-architecture` first.
 
-## 0. Map guard
+## 0. Pipeline State Check
+
+1. Read `.agent/progress/spec-pipeline.md`.
+   - If the file does not exist → **STOP**: "No pipeline tracker found. Run `/decompose-architecture` first."
+2. Identify all shards where the IA column = `not-started`.
+   - If none → **STOP**: "All IA shards are already complete. Next step: `/write-be-spec`."
+3. Auto-select the lowest-numbered `not-started` shard.
+4. Present: "Pipeline tracker shows **shard [NN — name]** is the next incomplete IA shard. Proceeding with this shard. Say 'override' to pick a different one."
+5. Use the selected shard as the target for all subsequent steps.
+
+---
+
+## 0.1. Map guard
 
 Read the surface stack map from `.agent/instructions/tech-stack.md`. Verify that the following have filled values:
 - **Databases** column (per-surface, any row)
@@ -33,7 +45,7 @@ If any are empty → **HARD STOP**: tell the user to run `/create-prd` first.
 
 ---
 
-## 0.5. Re-run check
+## 0.6. Re-run check
 
 Before loading skills, check whether the shard file at `docs/plans/ia/[shard-name].md` already has content beyond skeleton placeholders (look for filled-in sections vs empty `<!-- TODO -->` markers).
 
@@ -44,35 +56,23 @@ Before loading skills, check whether the shard file at `docs/plans/ia/[shard-nam
 
 ## 1. Explore requirements
 
-### 1a. Read the authoritative sources
+### 1a. Read authoritative sources
 
-Read the following files and build a **reconciliation table** comparing what each source says about this shard's features. Use the `ideation-index.md` Structure Map to find the correct domain folder path (may be under `domains/` or `surfaces/{name}/` for multi-product projects). The ideation domain's feature files are the **primary source of truth** for sub-features — the architecture design is secondary context.
+Build a **reconciliation table** comparing sources. Ideation domain feature files are **primary source of truth** — architecture design is secondary. Use `ideation-index.md` Structure Map for domain folder path.
 
-1. The relevant ideation domain folder for this shard (path from `ideation-index.md` Structure Map):
-   - Read the domain's `*-index.md` for the children table and Role Matrix
-   - Read each child **feature `.md` file** for sub-feature details (Role Lens, behavior, edge cases)
-   - Read the domain's `*-cx.md` for cross-domain interactions relevant to this shard
-   - If the domain has sub-domain folders, recurse into them and aggregate all descendant feature files
-2. The shard's `## Features` section (from `/decompose-architecture-structure`)
-3. `docs/plans/ideation/ideation-index.md` — Must Have features for this domain
+1. Ideation domain folder (path from Structure Map):
+   - `*-index.md` (children table + Role Matrix), each child feature `.md`, `*-cx.md`
+   - If sub-domain folders exist, recurse and aggregate all descendant feature files
+2. Shard's `## Features` section
+3. `docs/plans/ideation/ideation-index.md` — Must Have features
 
-Read `.agent/skills/spec-writing/SKILL.md` and `.agent/skills/architecture-mapping/SKILL.md`. Follow the architecture-mapping skill's Sub-Feature Reconciliation Protocol to build the reconciliation table and apply mismatch handling rules.
+Read `.agent/skills/spec-writing/SKILL.md` and `.agent/skills/architecture-mapping/SKILL.md`. Follow the Sub-Feature Reconciliation Protocol.
 
 ### 1b. Scope confirmation
 
-Present the reconciled `## Features` list to the user, including a count of newly added sub-features:
+Present reconciled features with counts of added (`[N]`) and architecture-only (`[M]`) sub-features. Ask: "Does this match your intent? Any to add, remove, or re-scope?" **Wait for confirmation.** Update shard file immediately on changes.
 
-> **Reconciled features for [Shard NN — Domain Name]:**
-> [bullet list of all sub-features, with `[Architecture-only]` markers]
-> 
-> **[N] sub-features added from ideation domain tree** that were missing from the shard skeleton.
-> **[M] sub-features marked `[Architecture-only]`** — not found in ideation domain tree, added during decomposition.
-> 
-> "Does this feature list match your intent for this domain? Any sub-features to add, remove, or re-scope?"
-
-**Wait for explicit user confirmation before proceeding.** If the user modifies the list, update the shard's `## Features` section in `docs/plans/ia/[shard-name].md` immediately.
-
-**Post-reconciliation calibration check**: Count confirmed sub-features. If **≥ 10**, follow the **Sub-Feature Complexity Split Protocol** in `.agent/skills/architecture-mapping/SKILL.md` — present the split proposal, wait for approval, redirect to `/decompose-architecture-validate`. Do NOT proceed to Step 2 with an oversized shard. **After any split**: run `/remediate-shard-split` — do NOT restart spec writing until zero stale parent references remain.
+**Post-reconciliation**: If **≥ 10** sub-features → follow Sub-Feature Complexity Split Protocol (`.agent/skills/architecture-mapping/SKILL.md`), redirect to `/decompose-architecture-validate`. **After any split**: run `/remediate-shard-split` before restarting.
 
 If the sub-feature count is **< 10**, proceed directly to Step 1c.
 
@@ -161,20 +161,11 @@ For each event's listed consumers: verify consumer shard exists in `docs/plans/i
 
 ## 7. Document edge cases
 
-Read .agent/skills/resolve-ambiguity/SKILL.md and follow its methodology.
-
-Read .agent/skills/adversarial-review/SKILL.md and follow its structured methodology for generating attack scenarios, abuse cases, race conditions, and security edge cases against this shard's interactions. Produce spec-level gap items for any identified risks.
-
-Read each skill listed in `{{SECURITY_SKILLS}}` (comma-separated). For each skill directory name, read `.agent/skills/[skill]/SKILL.md` before proceeding.
-For each skill in {{SECURITY_SKILLS}}, follow its attack surface methodology for edge case identification.
+Read and follow `.agent/skills/resolve-ambiguity/SKILL.md` and `.agent/skills/adversarial-review/SKILL.md` (attack scenarios, abuse cases, race conditions). Read each `{{SECURITY_SKILLS}}` skill and apply its attack surface methodology.
 
-- Rate limits and abuse scenarios
-- Concurrent access handling
-- Deletion cascades
-- State transition conflicts
-- Empty/null states
+Cover: rate limits/abuse, concurrent access, deletion cascades, state conflicts, empty/null states.
 
-**Review questions**: "What's the worst thing a malicious user could try in this domain?" / "What happens if two users do the same thing at the same time?" / "What happens when related data is deleted?"
+**Review questions**: "Worst thing a malicious user could try?" / "Two users do the same thing simultaneously?" / "What happens when related data is deleted?"
 
 ## 7.5. Write deep dive files (if applicable)
 

package/template/.agent/workflows/write-architecture-spec.md

@@ -39,6 +39,16 @@ Fill in a skeleton IA shard with full interaction details, data models, access c
 
 ## Orchestration
 
+### Step 0 — Pipeline State Check
+
+1. Read `.agent/progress/spec-pipeline.md`.
+   - If the file does not exist → **STOP**: "No pipeline tracker found. Run `/decompose-architecture` first."
+2. Identify all shards where the IA column = `not-started`.
+   - If none → **STOP**: "All IA shards are already complete. Next step: `/write-be-spec`."
+3. Auto-select the lowest-numbered `not-started` shard.
+4. Present: "Pipeline tracker shows **shard [NN — name]** is the next incomplete IA shard. Proceeding with this shard. Say 'override' to pick a different one."
+5. Pass the selected shard to Step A.
+
 ### Step A — Run `.agent/workflows/write-architecture-spec-design.md`
 
 Uses the brainstorming skill to clarify scope, then systematically designs all sections: interaction maps, contract shapes, data models, access control, event schemas, and edge cases. Each section is presented to the user for discussion and refinement.

package/template/.agent/workflows/write-be-spec-classify.md

@@ -24,13 +24,26 @@ Identify the target IA shard, classify it, load skills, and read all source mate
 
 ---
 
+## 0. Pipeline State Check
+
+1. Read `.agent/progress/spec-pipeline.md`.
+   - If the file does not exist → **STOP**: "No pipeline tracker found. Run `/decompose-architecture` first."
+2. Identify all shards where the BE column = `not-started` AND the IA column = `complete`.
+   - If no shards have IA `complete` → **STOP**: "IA layer not complete — run `/write-architecture-spec` first."
+   - If all eligible shards already have BE `complete` → **STOP**: "All BE specs are complete. Next step: `/write-fe-spec`."
+3. Auto-select the lowest-numbered eligible shard.
+4. Present: "Pipeline tracker shows **shard [NN — name]** is the next shard needing a BE spec. Proceeding. Say 'override' to pick a different one."
+5. Use the selected shard as the target for all subsequent steps.
+
+---
+
 ## 1. Verify IA layer is complete, then identify the target shard
 
 1. Read `docs/plans/ia/index.md`
 2. Check every shard's status column
 3. If any shard is not ✅ → **STOP**: list incomplete shards and redirect to `/write-architecture-spec`
 
-Determine which IA shard to process. Read it in full before proceeding.
+Determine which IA shard to process (using the shard selected in Step 0). Read it in full before proceeding.
 
 ## 2. Classify the shard
 

package/template/.agent/workflows/write-be-spec-write.md

@@ -154,7 +154,7 @@ If `docs/plans/feature-ledger.md` exists, read `.agent/skills/prd-templates/refe
 
 ## 13.7. Completion Gate (MANDATORY)
 
-1. Update `.agent/progress/spec-pipeline.md` — mark BE column for this shard as complete
+1. **Verify pipeline tracker** — Read `.agent/progress/spec-pipeline.md` and confirm the BE column for this shard shows `complete`. If it does not → **STOP**: "Pipeline tracker was not updated in Step 9. Go back and run Protocol 08 now before proceeding."
 2. Scan this conversation for memory-capture triggers (see rule: `memory-capture`):
    - Patterns observed → write to `memory/patterns.md`
    - Non-trivial decisions made → write to `memory/decisions.md`

package/template/.agent/workflows/write-be-spec.md

@@ -50,6 +50,17 @@ If a needed skill is missing, check if a matching entry exists in `.agent/skill-
 
 ## Orchestration
 
+### Step 0 — Pipeline State Check
+
+1. Read `.agent/progress/spec-pipeline.md`.
+   - If the file does not exist → **STOP**: "No pipeline tracker found. Run `/decompose-architecture` first."
+2. Identify all shards where the BE column = `not-started` AND the IA column = `complete`.
+   - If no shards have IA `complete` → **STOP**: "IA layer not complete — run `/write-architecture-spec` first."
+   - If all eligible shards already have BE `complete` → **STOP**: "All BE specs are complete. Next step: `/write-fe-spec`."
+3. Auto-select the lowest-numbered eligible shard.
+4. Present: "Pipeline tracker shows **shard [NN — name]** is the next shard needing a BE spec. Proceeding. Say 'override' to pick a different one."
+5. Pass the selected shard to Step A.
+
 ### Step A — Run `.agent/workflows/write-be-spec-classify.md`
 
 Identifies the target IA shard, classifies it (feature domain / multi-domain / cross-cutting / structural reference / composite), loads the skill bundle, reads all source material (primary shard, cross-shard references, deep dives, testability section), and reads cross-cutting specs.

package/template/.agent/workflows/write-fe-spec-classify.md

@@ -24,17 +24,30 @@ Identify the target FE spec, classify it, load skills, and read all source mater
 
 ---
 
-## 0. Placeholder guard
+## 0. Pipeline State Check
 
-Before any skill reads, verify that the five placeholder values listed in `requires_placeholders` frontmatter have been filled by `/bootstrap-agents`. For each placeholder, check whether the literal characters `{{` still appear in the value. If **any** are unfilled, emit a **HARD STOP** and do not proceed to Step 0.5.
+1. Read `.agent/progress/spec-pipeline.md`.
+   - If the file does not exist → **STOP**: "No pipeline tracker found. Run `/decompose-architecture` first."
+2. Identify all shards where the FE column = `not-started` AND the BE column = `complete`.
+   - If no shards have BE `complete` → **STOP**: "BE layer not complete — run `/write-be-spec` first."
+   - If all eligible shards already have FE `complete` → **STOP**: "All FE specs are complete. Next step: `/plan-phase`."
+3. Auto-select the lowest-numbered eligible shard.
+4. Present: "Pipeline tracker shows **shard [NN — name]** is the next shard needing an FE spec. Proceeding. Say 'override' to pick a different one."
+5. Use the selected shard as the target for all subsequent steps.
+
+---
+
+## 0.1. Placeholder guard
+
+Before any skill reads, verify that the five placeholder values listed in `requires_placeholders` frontmatter have been filled by `/bootstrap-agents`. For each placeholder, check whether the literal characters `{{` still appear in the value. If **any** are unfilled, emit a **HARD STOP** and do not proceed to Step 0.6.
 
 For the hard stop message format and recovery instructions, see `.agent/skills/prd-templates/references/placeholder-guard-template.md`. For placeholder-to-recovery mappings specific to this workflow, see `.agent/skills/session-continuity/protocols/10-placeholder-verification-gate.md`.
 
-Only proceed to Step 0.5 when all five placeholders report no literal `{{` characters.
+Only proceed to Step 0.6 when all five placeholders report no literal `{{` characters.
 
 ---
 
-## 0.5. Brand-guidelines prerequisite check
+## 0.6. Brand-guidelines prerequisite check
 
 1. Read `.agent/skills/brand-guidelines/SKILL.md`.
 2. Scan for any `{{PLACEHOLDER}}` values that are still unfilled. If any exist → stop and tell the user: _"Design direction hasn't been confirmed yet. Run `/create-prd` first to establish the design direction before writing FE specs."_
@@ -42,7 +55,7 @@ Only proceed to Step 0.5 when all five placeholders report no literal `{{` chara
 
 ---
 
-## 0.75. Design system prerequisite check
+## 0.8. Design system prerequisite check
 
 Read `.agent/skills/prd-templates/references/design-system-prerequisite-check.md` and follow its procedure. Extract all seven decision areas from `docs/plans/design-system.md` and run the fail-fast validation checks. If any check fails → stop and instruct the user to run `/create-prd-design-system`.
 

package/template/.agent/workflows/write-fe-spec-write.md

@@ -148,7 +148,7 @@ If `docs/plans/feature-ledger.md` exists, read `.agent/skills/prd-templates/refe
 
 ## 12.7. Completion Gate (MANDATORY)
 
-1. Update `.agent/progress/spec-pipeline.md` — mark FE column for this shard as complete
+1. **Verify pipeline tracker** — Read `.agent/progress/spec-pipeline.md` and confirm the FE column for this shard shows `complete`. If it does not → **STOP**: "Pipeline tracker was not updated in Step 8. Go back and run Protocol 08 now before proceeding."
 2. Scan this conversation for memory-capture triggers (see rule: `memory-capture`):
    - Patterns observed → write to `memory/patterns.md`
    - Non-trivial decisions made → write to `memory/decisions.md`

package/template/.agent/workflows/write-fe-spec.md

@@ -47,6 +47,17 @@ If a needed skill is missing, check if a matching entry exists in `.agent/skill-
 
 ## Orchestration
 
+### Step 0 — Pipeline State Check
+
+1. Read `.agent/progress/spec-pipeline.md`.
+   - If the file does not exist → **STOP**: "No pipeline tracker found. Run `/decompose-architecture` first."
+2. Identify all shards where the FE column = `not-started` AND the BE column = `complete`.
+   - If no shards have BE `complete` → **STOP**: "BE layer not complete — run `/write-be-spec` first."
+   - If all eligible shards already have FE `complete` → **STOP**: "All FE specs are complete. Next step: `/plan-phase`."
+3. Auto-select the lowest-numbered eligible shard.
+4. Present: "Pipeline tracker shows **shard [NN — name]** is the next shard needing an FE spec. Proceeding. Say 'override' to pick a different one."
+5. Pass the selected shard to Step A.
+
 ### Step A — Run `.agent/workflows/write-fe-spec-classify.md`
 
 Identifies the target FE spec, classifies it (feature spec / cross-cutting), loads the skill bundle, reads all source documents (BE spec, IA shard, cross-shard references, deep dives with FE implications), and reads cross-cutting FE specs.