66 lines
3.2 KiB
Markdown
66 lines
3.2 KiB
Markdown
# Task Plan & Specification Audit Protocol (`tasks/audit-1.md`)
|
|
|
|
This protocol defines the standard for auditing, grading, and refining new task
|
|
files in `tasks/new/` before implementation begins.
|
|
|
|
---
|
|
|
|
## 1. Direct Execution Protocol (When Running the Audit Yourself)
|
|
|
|
When commanded to **"Run Audit-1 on `[TASK_FILE]`"**:
|
|
|
|
1. **Remain Strictly Read-Only:** Do not modify any codebase files or task files
|
|
during the audit.
|
|
2. **Examine the Codebase:** Inspect the current architecture to verify if the
|
|
task's assumptions, dependencies, and target files are accurate.
|
|
3. **Score against the 5-Point Plan Rubric:**
|
|
- **Criterion 1 (Standards Compliance):** Adheres to `tasks/GUIDELINES.md`
|
|
naming conventions (`YYYY-MMDD.XX.agent.type.scope.title-HHMM.md`) and
|
|
contains the mandatory `# TASK METADATA` header.
|
|
- **Criterion 2 (Architectural Safety):** Identifies real technical risks
|
|
(event loop blocks, memory leaks, cache staleness, monolithic sprawl,
|
|
zero-trust bypasses) with mitigations.
|
|
- **Criterion 3 (Purity & Simplicity):** Evaluates native/simpler
|
|
alternatives and avoids dependency/code bloat.
|
|
- **Criterion 4 (Implementation Precision):** Target files, functions, SQL
|
|
schemas, and error boundaries are unambiguously specified.
|
|
- **Criterion 5 (Testing Rigor):** Includes unit/integration test plans
|
|
covering happy paths, edge cases, and 401/403 security gates.
|
|
4. **Output the Standard Audit Report:**
|
|
- **Overall Score / Rating:** [e.g. 5/5, 4/5, or Letter Grade]
|
|
- **Verdict:** [APPROVED / NEEDS REVISION / REJECTED]
|
|
- **Strengths & Plan Alignment:** What the plan gets right.
|
|
- **Identified Gaps & Failure Risks:** Missing edge cases, risks, or
|
|
regressions.
|
|
- **Concrete Suggested Revisions:** Exact text, parameters, or steps to
|
|
add/change in the task file.
|
|
|
|
---
|
|
|
|
## 2. Dispatch Template (When Preparing a Prompt for Jules or External Agents)
|
|
|
|
When commanded to **"Prepare an Audit-1 prompt for Jules"**, fill in and provide
|
|
the following block:
|
|
|
|
```text
|
|
**Role:** Act as a Principal Systems Architect and Task Quality Critic. Do not modify the codebase or execute code during this session. Your sole deliverable is a structured task critique report.
|
|
|
|
**The Scope:** Review the newly generated task file in `[tasks/new/TASK_FILENAME.md]` against our master architectural guidelines (`AGENTS.md`, `docs/`, `tasks/GUIDELINES.md`).
|
|
|
|
**Your Task:**
|
|
Critically evaluate the proposed task plan against the 5-point quality rubric in `tasks/audit-1.md`:
|
|
1. Metadata & Standards Compliance
|
|
2. Architectural Alignment & Safety
|
|
3. Purity & Simplicity (Avoiding bloat)
|
|
4. Implementation Precision & State Machine
|
|
5. Testing & Quality Gate Rigor
|
|
|
|
**Deliverable:**
|
|
Provide a structured critique report with:
|
|
- **Overall Score / Rating:** [e.g. 5/5, 4/5, or Letter Grade]
|
|
- **Verdict:** [APPROVED / NEEDS REVISION / REJECTED]
|
|
- **Strengths & Plan Alignment:** Key architectural insights captured in the plan.
|
|
- **Identified Gaps & Potential Risks:** Missing edge cases, unaddressed failure modes, or UX/architectural oversights.
|
|
- **Concrete Suggested Revisions:** Exact adjustments, additions, or rewordings to incorporate into the task file before implementation starts.
|
|
```
|