torusguard 1.3.4 → 1.3.5

package/skills/torusguard/payload/skills/torusguard-apply/SKILL.md

@@ -1,80 +1,84 @@
----
-name: torusguard-apply
-description: Apply governed remediation patches to disk with pre-apply rollback snapshots and Human Gate validation via CLI or AI Agent.
-version: 1.3.4
-workflow: .torusguard/workflows/apply.md
-tools: Read, Grep, Glob, Write, replace_file_content, run_command
-scripts-binding:
-  - .torusguard/scripts/apply_runner.py
-  - .torusguard/scripts/term_ui.py
-  - .torusguard/scripts/memory_engine.py
----
-
-# TorusGuard Apply — Governed Patch Application & Rollback Snapshot
-
-## Objective
-Safely apply approved remediation bundles to disk source files, creating an automated byte-for-byte pre-apply backup snapshot (`.bak`) in `.torusguard/snapshots/<run_id>/`, asserting syntax validity, and distilling passing patterns into Golden Fix Recipes.
-
----
-
-## Two Execution Modes
-
-### Mode A: Automated CLI Execution (Interactive or Non-Interactive)
-Run the governed patch applier from your terminal:
-```bash
-# Interactive Human Gate review (prompts for each patch: [y]es / [n]o / [a]ll / [q]uit)
-npx torusguard apply
-
-# Non-interactive automated application
-npx torusguard apply --yes
-
-# Apply patches from a specific run ID
-npx torusguard apply --run run-20260910-121618-audit --yes
-
-# Emergency rollback from pre-apply snapshot
-npx torusguard rollback
-# or
-npx torusguard apply --rollback
-```
-**Under the Hood:** Executes `python .torusguard/scripts/apply_runner.py`.
-1. Reads candidate bundles from `.torusguard/runs/<run_id>/bundles/`.
-2. Creates `.bak` snapshot in `.torusguard/snapshots/<run_id>/<rel_path>.bak`.
-3. Performs line-aware replacement without corrupting concurrent modifications.
-4. Distills the applied fix into a **Golden Fix Recipe** registered in `.torusguard/memory/patterns.json`.
-5. Emits `diff_summary.md` and `apply_plan.md` in the run directory.
-6. Displays pixel-perfect 75-column terminal cards.
-
-### Mode B: In-Session AI Chat Agent Application
-When applying patches directly within an AI chat session:
-1. **Human Gate Confirmation:** Present the unified diff to the operator and request explicit approval before editing code.
-2. **Pre-Apply Snapshot:** Ensure target file backup is created at `.torusguard/snapshots/<run_id>/<rel_path>.bak`.
-3. **Execute Surgical Edit:** Use `replace_file_content` to apply only the approved lines. Strictly adhere to the formulated Ponytail diff.
-4. **Syntax & Integrity Check:** Verify that the patched file is syntactically valid (e.g. `node --check <file>` or `python -m py_compile <file>`). If syntax fails, immediately restore from `.bak`.
-5. **Memory Registration:** Update persistent memory events in `.torusguard/memory/events.json` with event `fix_applied`.
-6. **Recommend Recheck:** Advise running `/torusguard recheck` or `npx torusguard recheck` to verify closure.
-
----
-
-## Rollback Guarantee
-If an applied patch introduces unexpected runtime behavior or breaks tests:
-```bash
-# Instant one-command rollback of the latest applied run:
-npx torusguard rollback
-
-# Or rollback a specific run:
-npx torusguard rollback --run run-20260910-121618-audit
-```
-All affected files are restored byte-for-byte from `.torusguard/snapshots/<run_id>/`.
-
----
-
-## Output Card Format
-```markdown
-### 🚀 TorusGuard Patch Applied Successfully
-- **Target File:** `server/index.js:9`
-- **Rule ID:** `TG-SEC-001` (Hardcoded JWT secret)
-- **Ponytail Churn:** +1 / -1
-- **Rollback Snapshot:** `.torusguard/snapshots/<run_id>/server/index.js.bak`
-- **Golden Recipe:** Distilled into persistent memory
-- **Next Step:** Run `npx torusguard recheck` or `/torusguard recheck` to verify closure
-```
+---
+name: torusguard-apply
+description: Apply governed remediation patches to disk with pre-apply rollback snapshots and Human Gate validation via CLI or AI Agent.
+version: 1.3.5
+workflow: .torusguard/workflows/apply.md
+tools: Read, Grep, Glob, Write, replace_file_content, run_command
+scripts-binding:
+  - .torusguard/scripts/report_sync.py
+  - .torusguard/scripts/apply_runner.py
+  - .torusguard/scripts/term_ui.py
+  - .torusguard/scripts/memory_engine.py
+---
+
+# TorusGuard Apply — Governed Patch Application & Rollback Snapshot
+
+## Objective
+Safely apply approved remediation bundles to disk source files, creating an automated byte-for-byte pre-apply backup snapshot (`.bak`) in `.torusguard/snapshots/<run_id>/`, asserting syntax validity, and distilling passing patterns into Golden Fix Recipes.
+
+---
+
+## Two Execution Modes
+
+### Mode A: Automated CLI Execution (Interactive or Non-Interactive)
+Run the governed patch applier from your terminal:
+```bash
+# Interactive Human Gate review (prompts for each patch: [y]es / [n]o / [a]ll / [q]uit)
+npx torusguard apply
+
+# Non-interactive automated application
+npx torusguard apply --yes
+
+# Apply patches from a specific run ID
+npx torusguard apply --run run-20260910-121618-audit --yes
+
+# Emergency rollback from pre-apply snapshot
+npx torusguard rollback
+# or
+npx torusguard apply --rollback
+```
+**Under the Hood:** Executes `python .torusguard/scripts/apply_runner.py`.
+1. Reads candidate bundles from `.torusguard/runs/<run_id>/bundles/`.
+2. Creates `.bak` snapshot in `.torusguard/snapshots/<run_id>/<rel_path>.bak`.
+3. Performs line-aware replacement without corrupting concurrent modifications.
+4. Distills the applied fix into a **Golden Fix Recipe** registered in `.torusguard/memory/patterns.json`.
+5. Emits `diff_summary.md` and `apply_plan.md` in the run directory.
+6. Displays pixel-perfect 75-column terminal cards.
+
+### Mode B: In-Session AI Chat Agent Application
+When applying patches directly within an AI chat session:
+1. **Human Gate Confirmation:** Present the unified diff to the operator and request explicit approval before editing code.
+2. **Pre-Apply Snapshot:** Ensure target file backup is created at `.torusguard/snapshots/<run_id>/<rel_path>.bak`.
+3. **Execute Surgical Edit:** Use `replace_file_content` to apply only the approved lines. Strictly adhere to the formulated Ponytail diff.
+4. **Syntax & Integrity Check:** Verify that the patched file is syntactically valid (e.g. `node --check <file>` or `python -m py_compile <file>`). If syntax fails, immediately restore from `.bak`.
+5. **Memory Registration:** Update persistent memory events in `.torusguard/memory/events.json` with event `fix_applied`.
+6. **Recommend Recheck:** Advise running `/torusguard recheck` or `npx torusguard recheck` to verify closure.
+
+---
+
+## Rollback Guarantee
+If an applied patch introduces unexpected runtime behavior or breaks tests:
+```bash
+# Instant one-command rollback of the latest applied run:
+npx torusguard rollback
+
+# Or rollback a specific run:
+npx torusguard rollback --run run-20260910-121618-audit
+```
+All affected files are restored byte-for-byte from `.torusguard/snapshots/<run_id>/`.
+
+---
+
+## Output Card Format
+```markdown
+### 🚀 TorusGuard Patch Applied Successfully
+- **Target File:** `server/index.js:9`
+- **Rule ID:** `TG-SEC-001` (Hardcoded JWT secret)
+- **Ponytail Churn:** +1 / -1
+- **Rollback Snapshot:** `.torusguard/snapshots/<run_id>/server/index.js.bak`
+- **Golden Recipe:** Distilled into persistent memory
+- **Next Step:** Run `npx torusguard recheck` or `/torusguard recheck` to verify closure
+```
+
+## Living Report Ground Truth
+- Read `security_report.md` in the workspace root before taking any action. Update the relevant finding card after completing remediation.

package/skills/torusguard/payload/skills/torusguard-audit/SKILL.md

@@ -1,83 +1,87 @@
----
-name: torusguard-audit
-description: Static AST security scanning, line-shift invariant fingerprinting, root-cause clustering, and 0-100 confidence scoring via CLI or AI Agent.
-version: 1.3.4
-workflow: .torusguard/workflows/audit.md
-tools: Read, Grep, Glob, Write, run_command
-scripts-binding:
-  - .torusguard/scripts/audit_runner.py
-  - .torusguard/scripts/term_ui.py
-  - .torusguard/scripts/finding_scorer.py
----
-
-# TorusGuard Audit — Static Code Security Analysis
-
-## Objective
-Execute static AST analysis across polyglot project files, evaluate code against 71 canonical security rules across 11 families, assign stable line-shift invariant fingerprints, cluster architectural root causes, and score findings with auditable 0–100 confidence ratings.
-
----
-
-## Two Execution Modes
-
-### Mode A: Automated CLI Execution
-Run the static security audit from your terminal:
-```bash
-# Scan current repository
-npx torusguard audit
-
-# Scan specific directory or example app
-npx torusguard audit ./examples/vulnerable-react-express
-
-# Include test fixtures and spec directories
-npx torusguard audit --include-tests
-
-# Output machine-readable JSON
-npx torusguard audit --json
-```
-**Under the Hood:** Executes `python .torusguard/scripts/audit_runner.py`.
-- Auto-detects repository stack and skips build/cache directories (`node_modules`, `.git`, `.venv`, `dist`, `build`).
-- Evaluates files across 11 canonical security families:
-  - `TG-SEC-*`: Hardcoded credentials, private keys, JWT secrets, client env leaks.
-  - `TG-INPUT-*`: SQL injection, command injection, path traversal, unsafe HTML rendering.
-  - `TG-DB-*`: Missing tenant isolation, service role keys in client code.
-  - `TG-AUTH-*`: Plaintext passwords, missing cookie security flags (httpOnly, secure, sameSite).
-  - `TG-PLATFORM-*`: Permissive wildcard CORS with credentials, missing security headers.
-  - `TG-DIFF-*`: Disabled TLS verification (`verify=False`, `rejectUnauthorized: false`).
-- Generates run directory: `.torusguard/runs/run-YYYYMMDD-HHMMSS-audit/`.
-- Writes `findings.json`, `findings.md`, and `manifest.json`.
-- Displays standardized 75-column terminal cards.
-- Returns exit code `1` if findings are discovered, `0` if clean.
-
-### Mode B: In-Session AI Chat Agent Scan
-When auditing files directly in AI chat:
-1. **Discover Sinks:** Use `grep_search` and `view_file` to search for dangerous patterns across server and client code.
-2. **Cluster Root Causes:** Group findings by causal architecture (e.g. `cluster-tenant-isolation`, `cluster-credentials-exposure`, `cluster-injection`).
-3. **Audit Evidence Sufficiency:** Ensure that user-controlled input reaches the vulnerable sink without prior sanitization or schema validation.
-4. **Present Actionable Findings:** Display finding cards with severity, rule ID, file, line, and remediation recommendation.
-5. **Prompt Next Phase:** Guide the operator to `/torusguard harden` or `npx torusguard harden`.
-
----
-
-## Canonical Rule Families
-| Family | Scope | Example Violations |
-| :--- | :--- | :--- |
-| **TG-SEC** | Secrets & Credentials | Hardcoded JWT secret, API key strings, token logging |
-| **TG-INPUT** | Injection & Input Validation | Raw SQL interpolation, DOM `innerHTML`, `path.join` traversal |
-| **TG-DB** | Database & Tenant Scoping | Unscoped `.objects.get(id=...)`, Prisma missing `tenantId` |
-| **TG-AUTH** | Authentication & Cookies | Insecure cookies (missing httpOnly/secure/sameSite) |
-| **TG-PLATFORM** | Server & Platform Config | Wildcard CORS (`origin: '*'`) with credentials |
-| **TG-DIFF** | Security Bypasses | Disabled TLS verification (`verify=False`) |
-
----
-
-## Output Card Format
-```markdown
-### 🛡️ TorusGuard Static Security Audit Completed
-- **Run ID:** `run-20260910-121618-audit`
-- **Scope:** 7 files evaluated across 11 canonical families
-- **Status:** ✖ CRITICAL FINDINGS DETECTED
-- **Findings:** 2 Critical, 2 High, 2 Medium/Low (6 total)
-- **Clusters:** 3 architectural root causes identified
-- **Artifacts:** `.torusguard/runs/<run_id>/findings.json`
-- **Next Action:** Run `npx torusguard harden` or `/torusguard harden`
-```
+---
+name: torusguard-audit
+description: Static AST security scanning, line-shift invariant fingerprinting, root-cause clustering, and 0-100 confidence scoring via CLI or AI Agent.
+version: 1.3.5
+workflow: .torusguard/workflows/audit.md
+tools: Read, Grep, Glob, Write, run_command
+scripts-binding:
+  - .torusguard/scripts/report_sync.py
+  - .torusguard/scripts/audit_runner.py
+  - .torusguard/scripts/term_ui.py
+  - .torusguard/scripts/finding_scorer.py
+---
+
+# TorusGuard Audit — Static Code Security Analysis
+
+## Objective
+Execute static AST analysis across polyglot project files, evaluate code against 74 canonical security rules across 11 families, assign stable line-shift invariant fingerprints, cluster architectural root causes, and score findings with auditable 0–100 confidence ratings.
+
+---
+
+## Two Execution Modes
+
+### Mode A: Automated CLI Execution
+Run the static security audit from your terminal:
+```bash
+# Scan current repository
+npx torusguard audit
+
+# Scan specific directory or example app
+npx torusguard audit ./examples/vulnerable-react-express
+
+# Include test fixtures and spec directories
+npx torusguard audit --include-tests
+
+# Output machine-readable JSON
+npx torusguard audit --json
+```
+**Under the Hood:** Executes `python .torusguard/scripts/audit_runner.py`.
+- Auto-detects repository stack and skips build/cache directories (`node_modules`, `.git`, `.venv`, `dist`, `build`).
+- Evaluates files across 18 canonical security families:
+  - `TG-SEC-*`: Hardcoded credentials, private keys, JWT secrets, client env leaks.
+  - `TG-INPUT-*`: SQL injection, command injection, path traversal, unsafe HTML rendering.
+  - `TG-DB-*`: Missing tenant isolation, service role keys in client code.
+  - `TG-AUTH-*`: Plaintext passwords, missing cookie security flags (httpOnly, secure, sameSite).
+  - `TG-PLATFORM-*`: Permissive wildcard CORS with credentials, missing security headers.
+  - `TG-DIFF-*`: Disabled TLS verification (`verify=False`, `rejectUnauthorized: false`).
+- Generates run directory: `.torusguard/runs/run-YYYYMMDD-HHMMSS-audit/`.
+- Writes `findings.json`, `findings.md`, and `manifest.json`.
+- Displays standardized 75-column terminal cards.
+- Returns exit code `1` if findings are discovered, `0` if clean.
+
+### Mode B: In-Session AI Chat Agent Scan
+When auditing files directly in AI chat:
+1. **Discover Sinks:** Use `grep_search` and `view_file` to search for dangerous patterns across server and client code.
+2. **Cluster Root Causes:** Group findings by causal architecture (e.g. `cluster-tenant-isolation`, `cluster-credentials-exposure`, `cluster-injection`).
+3. **Audit Evidence Sufficiency:** Ensure that user-controlled input reaches the vulnerable sink without prior sanitization or schema validation.
+4. **Present Actionable Findings:** Display finding cards with severity, rule ID, file, line, and remediation recommendation.
+5. **Prompt Next Phase:** Guide the operator to `/torusguard harden` or `npx torusguard harden`.
+
+---
+
+## Canonical Rule Families
+| Family | Scope | Example Violations |
+| :--- | :--- | :--- |
+| **TG-SEC** | Secrets & Credentials | Hardcoded JWT secret, API key strings, token logging |
+| **TG-INPUT** | Injection & Input Validation | Raw SQL interpolation, DOM `innerHTML`, `path.join` traversal |
+| **TG-DB** | Database & Tenant Scoping | Unscoped `.objects.get(id=...)`, Prisma missing `tenantId` |
+| **TG-AUTH** | Authentication & Cookies | Insecure cookies (missing httpOnly/secure/sameSite) |
+| **TG-PLATFORM** | Server & Platform Config | Wildcard CORS (`origin: '*'`) with credentials |
+| **TG-DIFF** | Security Bypasses | Disabled TLS verification (`verify=False`) |
+
+---
+
+## Output Card Format
+```markdown
+### 🛡️ TorusGuard Static Security Audit Completed
+- **Run ID:** `run-20260910-121618-audit`
+- **Scope:** 7 files evaluated across 11 canonical families
+- **Status:** ✖ CRITICAL FINDINGS DETECTED
+- **Findings:** 2 Critical, 2 High, 2 Medium/Low (6 total)
+- **Clusters:** 3 architectural root causes identified
+- **Artifacts:** `.torusguard/runs/<run_id>/findings.json`
+- **Next Action:** Run `npx torusguard harden` or `/torusguard harden`
+```
+
+## Living Report Ground Truth
+- Read `security_report.md` in the workspace root before taking any action. Update the relevant finding card after completing remediation.

package/skills/torusguard/payload/skills/torusguard-authorize/SKILL.md

@@ -1,10 +1,11 @@
 ---
 name: torusguard-authorize
 description: Register and validate runtime target authorization boundaries — scope boundaries, ownership proofs, TTL expiration, and Safety Gate enforcement.
-version: 1.3.4
+version: 1.3.5
 workflow: .torusguard/workflows/authorize.md
-tools: Read, Grep, Glob, Write
+tools: Read, Grep, Glob, Write, run_command
 scripts-binding:
+  - .torusguard/scripts/report_sync.py
   - .torusguard/scripts/safety_gate.py
 ---
 
@@ -30,6 +31,10 @@ Define and validate legal runtime authorization boundaries, verify target owners
 
 ---
 
+## Living Report Ground Truth
+- Always inspect `security_report.md` at workspace root before acting.
+- Update finding statuses after completion to eliminate hallucination.
+
 ## Safety Constraints
 - Never authorize wildcard hosts (`*`) or third-party domains.
 - State-changing destructive actions (`DELETE`, bulk drops) are disabled by default.

package/skills/torusguard/payload/skills/torusguard-exploit-check/SKILL.md

@@ -1,10 +1,11 @@
 ---
 name: torusguard-exploit-check
 description: Safe, non-destructive confirmation of exploitability using inert canary tokens and sentinels.
-version: 1.3.4
+version: 1.3.5
 workflow: .torusguard/workflows/exploit-check.md
-tools: Read, Grep, Glob, Bash, Write
+tools: Read, Grep, Glob, Bash, Write, run_command
 scripts-binding:
+  - .torusguard/scripts/report_sync.py
   - .torusguard/scripts/safety_gate.py
   - .torusguard/scripts/finding_scorer.py
 ---
@@ -48,6 +49,10 @@ Before dispatching any exploitability probe:
 
 ---
 
+## Living Report Ground Truth
+- Always inspect `security_report.md` at workspace root before acting.
+- Update finding statuses after completion to eliminate hallucination.
+
 ## Safety Constraints
 - Zero destructive payloads (`DROP`, `DELETE`, `UPDATE`).
 - No denial-of-service or continuous fuzzing loops.

package/skills/torusguard/payload/skills/torusguard-full/SKILL.md

@@ -1,10 +1,11 @@
 ---
 name: torusguard-full
 description: Master 7-stage security pipeline orchestrator — coordinates discovery, authorization, static audit, runtime validation, governed remediation, recheck, and reporting.
-version: 1.3.4
+version: 1.3.5
 workflow: .torusguard/workflows/audit.md
-tools: Read, Grep, Glob, Bash, Edit, Write
+tools: Read, Grep, Glob, Bash, Edit, Write, run_command
 scripts-binding:
+  - .torusguard/scripts/report_sync.py
   - .torusguard/scripts/stack_detect.py
   - .torusguard/scripts/safety_gate.py
   - .torusguard/scripts/finding_scorer.py
@@ -53,6 +54,10 @@ Evaluates Evidence (35 pts), Reproduction (25 pts), Corroboration (15 pts), Envi
 
 ---
 
+## Living Report Ground Truth
+- Always inspect `security_report.md` at workspace root before acting.
+- Update finding statuses after completion to eliminate hallucination.
+
 ## Safety & Governance
 - Human Gate mandatory before code modifications in Phase 5.
 - Enforce Ponytail line bounds ($\le 35$ additions, $\le 25$ deletions).

package/skills/torusguard/payload/skills/torusguard-harden/SKILL.md

@@ -1,94 +1,98 @@
----
-name: torusguard-harden
-description: Package surgical remediation bundles conforming to the Ponytail Protocol (<= 35 additions, <= 25 deletions) via CLI or AI Agent.
-version: 1.3.4
-workflow: .torusguard/workflows/harden.md
-tools: Read, Grep, Glob, Write, run_command
-scripts-binding:
-  - .torusguard/scripts/harden_runner.py
-  - .torusguard/scripts/diff_guard.py
-  - .torusguard/scripts/term_ui.py
----
-
-# TorusGuard Harden — Governed Remediation & Bundle Packaging
-
-## Objective
-Formulate minimal, surgical code fixes bound by the Ponytail Protocol ($\le 35$ additions, $\le 25$ deletions), packaging unified diffs into auditable remediation bundles ready for review.
-
----
-
-## Two Execution Modes
-
-### Mode A: Automated CLI Execution (Recommended First Step)
-Run the autonomous remediation engine via the terminal:
-```bash
-# Harden latest audit run
-npx torusguard harden
-
-# Harden specific project directory
-npx torusguard harden ./my-project
-
-# Harden specific run ID
-npx torusguard harden --run run-20260910-121618-audit
-
-# Machine-readable JSON output
-npx torusguard harden --json
-```
-**Under the Hood:** Executes `python .torusguard/scripts/harden_runner.py`.
-- Discovers findings in `.torusguard/runs/<run_id>/findings.json`.
-- Matches findings against canonical AST patch templates (`TG-SEC-*`, `TG-INPUT-*`, `TG-DB-*`, `TG-PLATFORM-*`, `TG-AUTH-*`, `TG-DIFF-*`).
-- Validates that every candidate patch strictly satisfies Ponytail bounds ($\le 35$ additions, $\le 25$ deletions).
-- Packages candidate bundles into `.torusguard/runs/<run_id>/bundles/<bundle_id>/` containing `patch.diff`, `minimal_patch_plan.md`, and `metadata.json`.
-- Emits run-level summary `remediation.md`.
-- Renders pixel-perfect 75-column terminal cards.
-
-### Mode B: In-Session AI Chat Agent Remediation
-When findings require complex architectural changes, or when the automated CLI cannot formulate a template match:
-1. **Locate Target Finding:** Inspect `.torusguard/runs/<run_id>/findings.md` or `findings.json`.
-2. **Inspect AST Context:** Read surrounding lines ($\pm 15$) of the vulnerable sink using `view_file`.
-3. **Formulate Minimal Fix:** Craft a surgical code modification:
-   - Parameterize SQL queries (replace concatenation with `?` or `$1` or `%s`).
-   - Add tenant isolation (`where: { tenantId }`, `organization_id=...`).
-   - Replace unsafe HTML injection (`dangerouslySetInnerHTML`, `.innerHTML = ...`) with safe text rendering (`textContent`, React elements).
-   - Sanitize path traversal using `path.basename()` or `os.path.basename()`.
-   - Constrain wildcard CORS headers to verified origin environment variables.
-   - Restore TLS verification flags (`verify=True`, `rejectUnauthorized: true`).
-4. **Validate Ponytail Bounds:** Count additions ($\le 35$) and deletions ($\le 25$). Never perform full-file rewrites.
-5. **Package Bundle Artifacts:** Write bundle under `.torusguard/runs/<run_id>/bundles/<bundle_id>/`:
-   - `patch.diff`: Standard unified diff.
-   - `minimal_patch_plan.md`: Context, rationale, and diff preview.
-   - `metadata.json`: Bundle metadata.
-6. **Report to Operator:** Present proposed diff card and recommend running `/torusguard apply` or `npx torusguard apply`.
-
----
-
-## Remediation Bundle Structure
-```
-.torusguard/runs/<run_id>/
-├── remediation.md                         # Run-level catalog of formulated candidate patches
-└── bundles/
-    └── bnd-<rule_id>-<line>-<hash>/
-        ├── patch.diff                    # Unified diff preview
-        ├── minimal_patch_plan.md         # Detailed explanation, rationale, and churn stats
-        └── metadata.json                 # Machine-readable bundle metadata
-```
-
----
-
-## Non-Negotiable Invariants
-- **Ponytail Limit:** Strict upper bound of $\le 35$ additions and $\le 25$ deletions per bundle.
-- **Dry-Run Rule:** Never modify target source code during `harden`. All edits must be reviewed before application in Phase 5 (`apply`).
-- **No Unrelated Churn:** Do not reformat unrelated code, reorder imports, or change styles.
-- **Zero Security Bypasses:** Never insert `# nosec`, `verify=False`, `[AllowAnonymous]`, or `csrf().disable()`.
-
----
-
-## Output Card Format
-```markdown
-### 🛠️ TorusGuard Remediation Bundle Formulated
-- **Target Finding:** `[TG-SEC-001]` at `server/index.js:9`
-- **Ponytail Churn:** +1 / -1 (Compliant <= 35 add, <= 25 del)
-- **Strategy:** Migrated hardcoded JWT secret to environment variable process.env.JWT_SECRET
-- **Bundle Directory:** `.torusguard/runs/<run_id>/bundles/bnd-tg-sec-001-9-a8310c/`
-- **Next Step:** Run `npx torusguard apply` or `/torusguard apply` to review and apply
-```
+---
+name: torusguard-harden
+description: Package surgical remediation bundles conforming to the Ponytail Protocol (<= 35 additions, <= 25 deletions) via CLI or AI Agent.
+version: 1.3.5
+workflow: .torusguard/workflows/harden.md
+tools: Read, Grep, Glob, Write, run_command
+scripts-binding:
+  - .torusguard/scripts/report_sync.py
+  - .torusguard/scripts/harden_runner.py
+  - .torusguard/scripts/diff_guard.py
+  - .torusguard/scripts/term_ui.py
+---
+
+# TorusGuard Harden — Governed Remediation & Bundle Packaging
+
+## Objective
+Formulate minimal, surgical code fixes bound by the Ponytail Protocol ($\le 35$ additions, $\le 25$ deletions), packaging unified diffs into auditable remediation bundles ready for review.
+
+---
+
+## Two Execution Modes
+
+### Mode A: Automated CLI Execution (Recommended First Step)
+Run the autonomous remediation engine via the terminal:
+```bash
+# Harden latest audit run
+npx torusguard harden
+
+# Harden specific project directory
+npx torusguard harden ./my-project
+
+# Harden specific run ID
+npx torusguard harden --run run-20260910-121618-audit
+
+# Machine-readable JSON output
+npx torusguard harden --json
+```
+**Under the Hood:** Executes `python .torusguard/scripts/harden_runner.py`.
+- Discovers findings in `.torusguard/runs/<run_id>/findings.json`.
+- Matches findings against canonical AST patch templates (`TG-SEC-*`, `TG-INPUT-*`, `TG-DB-*`, `TG-PLATFORM-*`, `TG-AUTH-*`, `TG-DIFF-*`).
+- Validates that every candidate patch strictly satisfies Ponytail bounds ($\le 35$ additions, $\le 25$ deletions).
+- Packages candidate bundles into `.torusguard/runs/<run_id>/bundles/<bundle_id>/` containing `patch.diff`, `minimal_patch_plan.md`, and `metadata.json`.
+- Emits run-level summary `remediation.md`.
+- Renders pixel-perfect 75-column terminal cards.
+
+### Mode B: In-Session AI Chat Agent Remediation
+When findings require complex architectural changes, or when the automated CLI cannot formulate a template match:
+1. **Locate Target Finding:** Inspect `.torusguard/runs/<run_id>/findings.md` or `findings.json`.
+2. **Inspect AST Context:** Read surrounding lines ($\pm 15$) of the vulnerable sink using `view_file`.
+3. **Formulate Minimal Fix:** Craft a surgical code modification:
+   - Parameterize SQL queries (replace concatenation with `?` or `$1` or `%s`).
+   - Add tenant isolation (`where: { tenantId }`, `organization_id=...`).
+   - Replace unsafe HTML injection (`dangerouslySetInnerHTML`, `.innerHTML = ...`) with safe text rendering (`textContent`, React elements).
+   - Sanitize path traversal using `path.basename()` or `os.path.basename()`.
+   - Constrain wildcard CORS headers to verified origin environment variables.
+   - Restore TLS verification flags (`verify=True`, `rejectUnauthorized: true`).
+4. **Validate Ponytail Bounds:** Count additions ($\le 35$) and deletions ($\le 25$). Never perform full-file rewrites.
+5. **Package Bundle Artifacts:** Write bundle under `.torusguard/runs/<run_id>/bundles/<bundle_id>/`:
+   - `patch.diff`: Standard unified diff.
+   - `minimal_patch_plan.md`: Context, rationale, and diff preview.
+   - `metadata.json`: Bundle metadata.
+6. **Report to Operator:** Present proposed diff card and recommend running `/torusguard apply` or `npx torusguard apply`.
+
+---
+
+## Remediation Bundle Structure
+```
+.torusguard/runs/<run_id>/
+├── remediation.md                         # Run-level catalog of formulated candidate patches
+└── bundles/
+    └── bnd-<rule_id>-<line>-<hash>/
+        ├── patch.diff                    # Unified diff preview
+        ├── minimal_patch_plan.md         # Detailed explanation, rationale, and churn stats
+        └── metadata.json                 # Machine-readable bundle metadata
+```
+
+---
+
+## Non-Negotiable Invariants
+- **Ponytail Limit:** Strict upper bound of $\le 35$ additions and $\le 25$ deletions per bundle.
+- **Dry-Run Rule:** Never modify target source code during `harden`. All edits must be reviewed before application in Phase 5 (`apply`).
+- **No Unrelated Churn:** Do not reformat unrelated code, reorder imports, or change styles.
+- **Zero Security Bypasses:** Never insert `# nosec`, `verify=False`, `[AllowAnonymous]`, or `csrf().disable()`.
+
+---
+
+## Output Card Format
+```markdown
+### 🛠️ TorusGuard Remediation Bundle Formulated
+- **Target Finding:** `[TG-SEC-001]` at `server/index.js:9`
+- **Ponytail Churn:** +1 / -1 (Compliant <= 35 add, <= 25 del)
+- **Strategy:** Migrated hardcoded JWT secret to environment variable process.env.JWT_SECRET
+- **Bundle Directory:** `.torusguard/runs/<run_id>/bundles/bnd-tg-sec-001-9-a8310c/`
+- **Next Step:** Run `npx torusguard apply` or `/torusguard apply` to review and apply
+```
+
+## Living Report Ground Truth
+- Read `security_report.md` in the workspace root before taking any action. Update the relevant finding card after completing remediation.