@undeemed/get-shit-done-codex 1.20.9 → 1.21.0

package/.codex/config.toml

@@ -0,0 +1,77 @@
+:schema https://developers.openai.com/codex/config-schema.json
+
+# Project-scoped Codex config for get-shit-done-codex.
+# Loaded only when this project is trusted.
+# Docs:
+# - https://developers.openai.com/codex/config-basic
+# - https://developers.openai.com/codex/config-reference
+# - https://developers.openai.com/codex/multi-agent
+
+web_search = "live"
+
+[features]
+multi_agent = true
+collaboration_modes = true
+shell_tool = true
+shell_snapshot = true
+unified_exec = true
+apply_patch_freeform = true
+personality = true
+request_rule = true
+
+[agents]
+max_threads = 12
+max_depth = 3
+
+[agents."general-purpose"]
+description = "General fallback role for GSD orchestration and ad-hoc subtasks."
+
+[agents."gsd-codebase-mapper"]
+description = "Map stack, architecture, conventions, testing, and concerns into .planning/codebase docs."
+developer_instructions = "Read and follow agents/gsd-codebase-mapper.md for your complete role definition."
+
+[agents."gsd-debugger"]
+description = "Investigate regressions with hypothesis testing, isolate root cause, and propose or apply fixes."
+developer_instructions = "Read and follow agents/gsd-debugger.md for your complete role definition."
+
+[agents."gsd-executor"]
+description = "Execute PLAN.md tasks with atomic commits, verification, and summary updates."
+developer_instructions = "Read and follow agents/gsd-executor.md for your complete role definition."
+
+[agents."gsd-integration-checker"]
+description = "Verify cross-phase wiring and end-to-end behavior across delivered milestones."
+developer_instructions = "Read and follow agents/gsd-integration-checker.md for your complete role definition."
+
+[agents."gsd-phase-researcher"]
+description = "Research phase implementation patterns and write RESEARCH.md artifacts for planners."
+developer_instructions = "Read and follow agents/gsd-phase-researcher.md for your complete role definition."
+
+[agents."gsd-plan-checker"]
+description = "Stress-test plan quality and requirement coverage before execution."
+developer_instructions = "Read and follow agents/gsd-plan-checker.md for your complete role definition."
+
+[agents."gsd-planner"]
+description = "Draft atomic PLAN.md files with objective, context, tasks, and success criteria."
+developer_instructions = "Read and follow agents/gsd-planner.md for your complete role definition."
+
+[agents."gsd-project-researcher"]
+description = "Research ecosystem and produce project-level research docs for roadmap creation."
+developer_instructions = "Read and follow agents/gsd-project-researcher.md for your complete role definition."
+
+[agents."gsd-research-synthesizer"]
+description = "Synthesize parallel research artifacts into actionable roadmap inputs."
+developer_instructions = "Read and follow agents/gsd-research-synthesizer.md for your complete role definition."
+
+[agents."gsd-roadmapper"]
+description = "Turn requirements into phased ROADMAP.md structure with clear success criteria."
+developer_instructions = "Read and follow agents/gsd-roadmapper.md for your complete role definition."
+
+[agents."gsd-verifier"]
+description = "Perform goal-backward verification that outcomes are actually delivered in code."
+developer_instructions = "Read and follow agents/gsd-verifier.md for your complete role definition."
+
+[mcp_servers.context7]
+url = "https://mcp.context7.com/mcp"
+
+[mcp_servers.context7.env_http_headers]
+CONTEXT7_API_KEY = "CONTEXT7_API_KEY"

package/README.md

@@ -4,6 +4,9 @@ A meta-prompting, context engineering and spec-driven development system for [Op
 
 Fork of [get-shit-done](https://github.com/taches/get-shit-done) by TÂCHES, adapted for Codex CLI by [undeemed](https://github.com/undeemed).
 
+> [!CAUTION]
+> As of February 25, 2026, Codex is supported upstream. This fork remains focused on Codex-specific UX and compatibility with extra goodies.
+
 [![npm version](https://img.shields.io/npm/v/%40undeemed%2Fget-shit-done-codex?style=flat-square)](https://www.npmjs.com/package/@undeemed/get-shit-done-codex)
 [![License](https://img.shields.io/badge/license-MIT-green?style=flat-square)](LICENSE)
 ![npm Downloads](https://img.shields.io/npm/dt/@undeemed/get-shit-done-codex?style=flat-square)
@@ -16,34 +19,123 @@ get-shit-done-codex (GSD) solves context rot — the quality degradation that ha
 
 **The solution:** Hierarchical planning with fresh context windows. Each task runs in isolation with exactly the context it needs—no degradation from accumulated garbage.
 
+## What Changed In This Fork
+
+- **AGENTS-first for Codex:** `AGENTS.md` is the primary behavior contract . [Agent.md > Skills.md](https://vercel.com/blog/agents-md-outperforms-skills-in-our-agent-evals)
+- **Two command surfaces:** choose native skills (`$gsd-*`) or prompt aliases (`/prompts:gsd-*`).
+- **Installer integrity checks:** `--verify` audits installation health, `--repair` restores missing artifacts.
+- **Mode-aware installs:** installer adapts `AGENTS.md` and command guidance to your chosen mode.
+
 ## Installation
 
 ```bash
 npx @undeemed/get-shit-done-codex@latest
 ```
 
-You'll be prompted to install globally (`~/.codex/`) or locally (`./`).
+You can install globally (`~/.codex/`) or locally (`./`).
+
+### Recommended
+
+```bash
+npx @undeemed/get-shit-done-codex --global
+```
+
+If you run this in an interactive terminal, the installer will prompt you to choose `skills` (`$`) or `prompts` (`/prompts`).
+In non-interactive runs, default is `skills` mode.
 
 For non-interactive installs:
 
 ```bash
 npx @undeemed/get-shit-done-codex --global   # Install to ~/.codex/
 npx @undeemed/get-shit-done-codex --local    # Install to current directory
+npx @undeemed/get-shit-done-codex --global --codex-mode skills   # Native skills only
+npx @undeemed/get-shit-done-codex --global --codex-mode prompts  # Prompt aliases only
+npx @undeemed/get-shit-done-codex --global --migrate             # Apply detected migration cleanup
+npx @undeemed/get-shit-done-codex --global --skip-migrate        # Keep legacy surface files
+npx @undeemed/get-shit-done-codex --verify --global              # Check install integrity
+npx @undeemed/get-shit-done-codex --verify --repair --global     # Auto-repair
+```
+
+### Codex Modes
+
+| Mode               | Installs                | Use Commands Like                |
+| ------------------ | ----------------------- | -------------------------------- |
+| `skills` (default) | `skills/gsd-*/SKILL.md` | `$gsd-help`, `$gsd-plan-phase 1` |
+| `prompts`          | `prompts/gsd-*.md`      | `/prompts:gsd-help`              |
+
+After installation, run `codex` (CLI) or `codex app` (Desktop), then run `$gsd-help` (or `/prompts:gsd-help` in prompts mode).
+Single-surface policy: mixed `skills/` + `prompts/` installs are treated as drift and fail `--verify`.
+
+### What Gets Installed
+
+The installer distributes everything GSD needs:
+
+- **`AGENTS.md`** — behavior contract and command reference for Codex
+- **`.codex/config.toml`** — multi-agent mode, feature flags, agent role registry, MCP servers
+- **`agents/gsd-*.md`** — rich agent definitions (700+ lines each) for sub-agent orchestration
+- **`skills/gsd-*/SKILL.md`** or **`prompts/gsd-*.md`** — command surfaces
+- **`get-shit-done/`** — workflow files, templates, and references
+
+On first run, Codex will prompt you to **trust the project** so the config takes effect (one-time, one-click).
+
+> [!NOTE]
+> `.codex/config.toml` is non-destructive — the installer skips it if you already have one, so your customizations are preserved on updates.
+
+### Installed File Structure
+
+`$` skills mode (`--codex-mode skills`, default):
+
+```text
+~/.codex/
+├── AGENTS.md
+├── .codex/config.toml
+├── agents/gsd-*.md
+├── skills/gsd-*/SKILL.md
+└── get-shit-done/
+```
+
+`/prompts` mode (`--codex-mode prompts`):
+
+```text
+~/.codex/
+├── AGENTS.md
+├── .codex/config.toml
+├── agents/gsd-*.md
+├── prompts/gsd-*.md
+└── get-shit-done/
 ```
 
-After installation, run `codex` (CLI) or `codex app` (Desktop), then use `/prompts:gsd-help` to see all commands.
+For local installs, replace `~/.codex/` with `./`.
+
+### Verify And Repair
+
+- `--verify`: checks `AGENTS.md`, `config.toml`, agent definitions, command surfaces, workflow assets, and version metadata.
+- `--verify --repair`: reinstalls missing/broken artifacts and verifies again.
+- Migration is **detect-then-confirm**, not automatic:
+  - Interactive install asks before removing legacy surface files
+  - Non-interactive install skips cleanup unless `--migrate` is passed
+  - `--skip-migrate` keeps legacy files explicitly
+
+### AGENTS-First Reliability
+
+This fork is intentionally **AGENTS.md-first** for Codex reliability:
+
+- `AGENTS.md` is the source of truth for behavior and workflow constraints
+- `$gsd-*` skills are lightweight command wrappers around the same workflow docs
+- `/prompts:gsd-*` are optional compatibility aliases (prompts mode)
 
 ## Staying Updated
 
 ```bash
 # Check for updates from inside Codex
-/prompts:gsd-update
+$gsd-update
+# or: /prompts:gsd-update
 
 # Update from terminal
 npx @undeemed/get-shit-done-codex@latest --global
 ```
 
-The installer now writes a `get-shit-done/VERSION` file so `/prompts:gsd-update` can detect installed vs latest and show changelog before updating.
+The installer writes a `get-shit-done/VERSION` file so `$gsd-update` (or `/prompts:gsd-update`) can detect installed vs latest and show changelog before updating.
 
 ## npm Trusted Publisher (OIDC)
 
@@ -63,16 +155,16 @@ When setting up npm Trusted Publisher for this package, use:
 
 ```bash
 # 1. Initialize project (questions → research → requirements → roadmap)
-/prompts:gsd-new-project
+$gsd-new-project
 
 # 2. Plan the first phase
-/prompts:gsd-plan-phase 1
+$gsd-plan-phase 1
 
 # 3. Execute the phase
-/prompts:gsd-execute-phase 1
+$gsd-execute-phase 1
 
 # 4. Verify it works
-/prompts:gsd-verify-work 1
+$gsd-verify-work 1
 ```
 
 ## How It Works
@@ -80,7 +172,7 @@ When setting up npm Trusted Publisher for this package, use:
 ### 1. Initialize Project
 
 ```
-/prompts:gsd-new-project
+$gsd-new-project
 ```
 
 One command takes you from idea to ready-for-planning:
@@ -95,7 +187,7 @@ One command takes you from idea to ready-for-planning:
 ### 2. Plan Phase
 
 ```
-/prompts:gsd-plan-phase 1
+$gsd-plan-phase 1
 ```
 
 The system researches how to implement the phase, creates 2-3 atomic task plans, and verifies them against requirements.
@@ -105,7 +197,7 @@ The system researches how to implement the phase, creates 2-3 atomic task plans,
 ### 3. Execute Phase
 
 ```
-/prompts:gsd-execute-phase 1
+$gsd-execute-phase 1
 ```
 
 Runs all plans in parallel waves. Each plan executes in a fresh 200k context window. Every task gets its own atomic commit.
@@ -115,26 +207,22 @@ Runs all plans in parallel waves. Each plan executes in a fresh 200k context win
 ### 4. Verify Work
 
 ```
-/prompts:gsd-verify-work 1
+$gsd-verify-work 1
 ```
 
 Manual user acceptance testing. The system walks you through testable deliverables and creates fix plans if issues are found.
 
 ## Commands
 
-| Command                             | Description                                                       |
-| ----------------------------------- | ----------------------------------------------------------------- |
-| `/prompts:gsd-new-project`          | Initialize project: questions → research → requirements → roadmap |
-| `/prompts:gsd-plan-phase [N]`       | Research + plan + verify for a phase                              |
-| `/prompts:gsd-execute-phase <N>`    | Execute all plans in parallel waves                               |
-| `/prompts:gsd-verify-work [N]`      | Manual user acceptance testing                                    |
-| `/prompts:gsd-complete-milestone`   | Archive milestone, tag release                                    |
-| `/prompts:gsd-new-milestone [name]` | Start next version                                                |
-| `/prompts:gsd-progress`             | Show current status and what's next                               |
-| `/prompts:gsd-update`               | Check npm for a newer release and apply update                    |
-| `/prompts:gsd-help`                 | Show all commands                                                 |
+| Command                  | Description                                                       |
+| ------------------------ | ----------------------------------------------------------------- |
+| `$gsd-new-project`       | Initialize project: questions → research → requirements → roadmap |
+| `$gsd-plan-phase [N]`    | Research + plan + verify for a phase                              |
+| `$gsd-execute-phase <N>` | Execute all plans in parallel waves                               |
+| `$gsd-verify-work [N]`   | Manual user acceptance testing                                    |
+| `$gsd-help`              | Show all commands                                                 |
 
-See `/prompts:gsd-help` for the complete command reference.
+Use `/prompts:gsd-*` aliases when installed with `--codex-mode prompts`.
 
 ## Why It Works
 
@@ -176,8 +264,15 @@ Git bisect finds exact failing task. Each task independently revertable.
 
 **Commands not found?**
 
-- Restart Codex CLI to reload prompts
-- Check `~/.codex/prompts/gsd-*.md` (global) or `./prompts/gsd-*.md` (local)
+- Restart Codex to reload installed command surfaces
+- Check `~/.codex/skills/gsd-*/SKILL.md` (global) or `./skills/gsd-*/SKILL.md` (local)
+- If using prompt aliases, check `~/.codex/prompts/gsd-*.md` (global) or `./prompts/gsd-*.md` (local)
+
+**Multi-agent / sub-agents not working?**
+
+- Check `.codex/config.toml` exists in your install directory
+- Ensure the project is **trusted** in Codex (it prompts on first run)
+- Run `--verify` to check all artifacts are present
 
 **Update to latest:**
 
@@ -188,7 +283,7 @@ npx @undeemed/get-shit-done-codex@latest
 **Can users be notified when an update is available?**
 
 - Yes. The installer prints an update notice if a newer npm version exists.
-- In-Codex update checks are available via `/prompts:gsd-update`.
+- In-Codex update checks are available via `$gsd-update` (or `/prompts:gsd-update`).
 - For release notifications outside the CLI, enable GitHub release watching on this repo.
 
 ## More Documentation
@@ -205,9 +300,9 @@ The original repository contains:
 
 **Note:** The original README is written for Codex Code. When following it, remember that this fork uses:
 
-- `/prompts:gsd-*` command format (instead of `/gsd:*`)
-- OpenAI Codex CLI & Desktop (instead of Codex Code)
-- `~/.codex/` directory (instead of `~/.codex/`)
+- Codex-native skills (`$gsd-*`) by default
+- Optional prompt aliases (`/prompts:gsd-*`) via `--codex-mode prompts`
+- OpenAI Codex CLI & Desktop
 
 ## Keywords
 

package/agents/gsd-debugger.md

@@ -740,7 +740,7 @@ DEBUG_RESOLVED_DIR=.planning/debug/resolved
 
 ```markdown
 ---
-status: gathering | investigating | fixing | verifying | resolved
+status: gathering | investigating | fixing | verifying | awaiting_human_verify | resolved
 trigger: "[verbatim user input]"
 created: [ISO timestamp]
 updated: [ISO timestamp]
@@ -804,10 +804,10 @@ files_changed: []
 ## Status Transitions
 
 ```
-gathering -> investigating -> fixing -> verifying -> resolved
-                  ^            |           |
-                  |____________|___________|
-                  (if verification fails)
+gathering -> investigating -> fixing -> verifying -> awaiting_human_verify -> resolved
+                  ^            |           |                 |
+                  |____________|___________|_________________|
+                  (if verification fails or user reports issue)
 ```
 
 ## Resume Behavior
@@ -910,6 +910,7 @@ Based on status:
 - "investigating" -> Continue investigation_loop from Current Focus
 - "fixing" -> Continue fix_and_verify
 - "verifying" -> Continue verification
+- "awaiting_human_verify" -> Wait for checkpoint response and either finalize or continue investigation
 </step>
 
 <step name="return_diagnosis">
@@ -969,11 +970,52 @@ Update status to "fixing".
 - Update status to "verifying"
 - Test against original Symptoms
 - If verification FAILS: status -> "investigating", return to investigation_loop
-- If verification PASSES: Update Resolution.verification, proceed to archive_session
+- If verification PASSES: Update Resolution.verification, proceed to request_human_verification
+</step>
+
+<step name="request_human_verification">
+**Require user confirmation before marking resolved.**
+
+Update status to "awaiting_human_verify".
+
+Return:
+
+```markdown
+## CHECKPOINT REACHED
+
+**Type:** human-verify
+**Debug Session:** .planning/debug/{slug}.md
+**Progress:** {evidence_count} evidence entries, {eliminated_count} hypotheses eliminated
+
+### Investigation State
+
+**Current Hypothesis:** {from Current Focus}
+**Evidence So Far:**
+- {key finding 1}
+- {key finding 2}
+
+### Checkpoint Details
+
+**Need verification:** confirm the original issue is resolved in your real workflow/environment
+
+**Self-verified checks:**
+- {check 1}
+- {check 2}
+
+**How to check:**
+1. {step 1}
+2. {step 2}
+
+**Tell me:** "confirmed fixed" OR what's still failing
+```
+
+Do NOT move file to `resolved/` in this step.
 </step>
 
 <step name="archive_session">
-**Archive resolved debug session.**
+**Archive resolved debug session after human confirmation.**
+
+Only run this step when checkpoint response confirms the fix works end-to-end.
 
 Update status to "resolved".
 
@@ -1130,6 +1172,8 @@ Orchestrator presents checkpoint to user, gets response, spawns fresh continuati
 **Commit:** {hash}
 ```
 
+Only return this after human verification confirms the fix.
+
 ## INVESTIGATION INCONCLUSIVE
 
 ```markdown
@@ -1179,7 +1223,8 @@ Check for mode flags in prompt context:
 **goal: find_and_fix** (default)
 - Find root cause, then fix and verify
 - Complete full debugging cycle
-- Archive session when verified
+- Require human-verify checkpoint after self-verification
+- Archive session only after user confirmation
 
 **Default mode (no flags):**
 - Interactive debugging with user

package/agents/gsd-planner.md

@@ -157,21 +157,19 @@ Every task has four required fields:
 - Good: "Create POST endpoint accepting {email, password}, validates using bcrypt against User table, returns JWT in httpOnly cookie with 15-min expiry. Use jose library (not jsonwebtoken - CommonJS issues with Edge runtime)."
 - Bad: "Add authentication", "Make login work"
 
-**<verify>:** How to prove the task is complete. Supports structured format:
+**<verify>:** How to prove the task is complete.
 
 ```xml
 <verify>
   <automated>pytest tests/test_module.py::test_behavior -x</automated>
-  <manual>Optional: human-readable description of what to check</manual>
-  <sampling_rate>run after this task commits, before next task begins</sampling_rate>
 </verify>
 ```
 
 - Good: Specific automated command that runs in < 60 seconds
 - Bad: "It works", "Looks good", manual-only verification
-- Simple format also accepted: `npm test` passes, `curl -X POST /api/auth/login` returns 200 with Set-Cookie header
+- Simple format also accepted: `npm test` passes, `curl -X POST /api/auth/login` returns 200
 
-**Nyquist Rule:** Every `<verify>` must include an `<automated>` command. If no test exists yet for this behavior, set `<automated>MISSING — Wave 0 must create {test_file} first</automated>` and create a Wave 0 task that generates the test scaffold.
+**Nyquist Rule:** Every `<verify>` must include an `<automated>` command. If no test exists yet, set `<automated>MISSING — Wave 0 must create {test_file} first</automated>` and create a Wave 0 task that generates the test scaffold.
 
 **<done>:** Acceptance criteria - measurable state of completion.
 - Good: "Valid credentials return 200 + JWT cookie, invalid credentials return 401"
@@ -202,6 +200,16 @@ Each task: **15-60 minutes** Codex execution time.
 
 **Combine signals:** One task sets up for the next, separate tasks touch same file, neither meaningful alone.
 
+## Interface-First Task Ordering
+
+When a plan creates new interfaces consumed by subsequent tasks:
+
+1. **First task: Define contracts** — Create type files, interfaces, exports
+2. **Middle tasks: Implement** — Build against the defined contracts
+3. **Last task: Wire** — Connect implementations to consumers
+
+This prevents the "scavenger hunt" anti-pattern where executors explore the codebase to understand contracts. They receive the contracts in the plan itself.
+
 ## Specificity Examples
 
 | TOO VAGUE | JUST RIGHT |
@@ -447,6 +455,69 @@ After completion, create `.planning/phases/XX-name/{phase}-{plan}-SUMMARY.md`
 
 Wave numbers are pre-computed during planning. Execute-phase reads `wave` directly from frontmatter.
 
+## Interface Context for Executors
+
+**Key insight:** "The difference between handing a contractor blueprints versus telling them 'build me a house.'"
+
+When creating plans that depend on existing code or create new interfaces consumed by other plans:
+
+### For plans that USE existing code:
+After determining `files_modified`, extract the key interfaces/types/exports from the codebase that executors will need:
+
+```bash
+# Extract type definitions, interfaces, and exports from relevant files
+grep -n "export\|interface\|type\|class\|function" {relevant_source_files} 2>/dev/null | head -50
+```
+
+Embed these in the plan's `<context>` section as an `<interfaces>` block:
+
+```xml
+<interfaces>
+<!-- Key types and contracts the executor needs. Extracted from codebase. -->
+<!-- Executor should use these directly — no codebase exploration needed. -->
+
+From src/types/user.ts:
+```typescript
+export interface User {
+  id: string;
+  email: string;
+  name: string;
+  createdAt: Date;
+}
+```
+
+From src/api/auth.ts:
+```typescript
+export function validateToken(token: string): Promise<User | null>;
+export function createSession(user: User): Promise<SessionToken>;
+```
+</interfaces>
+```
+
+### For plans that CREATE new interfaces:
+If this plan creates types/interfaces that later plans depend on, include a "Wave 0" skeleton step:
+
+```xml
+<task type="auto">
+  <name>Task 0: Write interface contracts</name>
+  <files>src/types/newFeature.ts</files>
+  <action>Create type definitions that downstream plans will implement against. These are the contracts — implementation comes in later tasks.</action>
+  <verify>File exists with exported types, no implementation</verify>
+  <done>Interface file committed, types exported</done>
+</task>
+```
+
+### When to include interfaces:
+- Plan touches files that import from other modules → extract those module's exports
+- Plan creates a new API endpoint → extract the request/response types
+- Plan modifies a component → extract its props interface
+- Plan depends on a previous plan's output → extract the types from that plan's files_modified
+
+### When to skip:
+- Plan is self-contained (creates everything from scratch, no imports)
+- Plan is pure configuration (no code interfaces involved)
+- Level 0 discovery (all patterns already established)
+
 ## Context Section Rules
 
 Only include prior plan SUMMARY references if genuinely needed (uses types/exports from prior plan, or prior plan made decision affecting this one).
@@ -956,6 +1027,16 @@ For phases not selected, retain from digest:
 - `patterns`: Conventions to follow
 
 **From STATE.md:** Decisions → constrain approach. Pending todos → candidates.
+
+**From RETROSPECTIVE.md (if exists):**
+```bash
+cat .planning/RETROSPECTIVE.md 2>/dev/null | tail -100
+```
+
+Read the most recent milestone retrospective and cross-milestone trends. Extract:
+- **Patterns to follow** from "What Worked" and "Patterns Established"
+- **Patterns to avoid** from "What Was Inefficient" and "Key Lessons"
+- **Cost patterns** to inform model selection and agent strategy
 </step>
 
 <step name="gather_phase_context">

package/agents/gsd-verifier.md

@@ -16,6 +16,21 @@ If the prompt contains a `<files_to_read>` block, you MUST use the `Read` tool t
 **Critical mindset:** Do NOT trust SUMMARY.md claims. SUMMARYs document what Codex SAID it did. You verify what ACTUALLY exists in the code. These often differ.
 </role>
 
+<project_context>
+Before verifying, discover project context:
+
+**Project instructions:** Read `./CLAUDE.md` if it exists in the working directory. Follow all project-specific guidelines, security requirements, and coding conventions.
+
+**Project skills:** Check `.agents/skills/` directory if it exists:
+1. List available skills (subdirectories)
+2. Read `SKILL.md` for each skill (lightweight index ~130 lines)
+3. Load specific `rules/*.md` files as needed during verification
+4. Do NOT load full `AGENTS.md` files (100KB+ context cost)
+5. Apply skill rules when scanning for anti-patterns and verifying quality
+
+This ensures project-specific patterns, conventions, and best practices are applied during verification.
+</project_context>
+
 <core_principle>
 **Task completion ≠ Goal achievement**