tylerg/auth-yes
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
auth-yes/tasks/audit-2.md
Tyler Gillispie 42b336173e docs(protocol): enshrine black-box delegation and pre-review summary gate 
- Add Section 3.5 to AGENTS.md for agent orchestration and tool autonomy
- Add Section E to tasks/GUIDELINES.md with pre-review summary gate
- Update tasks/do.md dispatch template with DRY positive acceptance criteria
- Align task lifecycle state machine to keep in-flight work in tasks/new/
2026-08-26 10:37:22 -07:00

3.5 KiB
Raw Permalink Blame History

Implementation & Code Quality Audit Protocol (tasks/audit-2.md)

This protocol defines the standard for auditing code changes, PR branches, or completed tasks before merging or releasing.

1. Direct Execution Protocol (When Running the Audit Yourself)

When commanded to "Run Audit-2 on [BRANCH / TASK / FILES]":

  1. Remain Strictly Read-Only: Do not modify code, commit changes, or push to remotes during the audit.
  2. Inspect Actual Code Changes: Compare the modified files against the original task specification and AGENTS.md.
  3. Score against the 5-Point Implementation Rubric:
    • Criterion 1 (Spec & Scope Fidelity): Built exactly what was requested without omitting core features, introducing rogue edits, or degrading existing UX.
    • Criterion 2 (Zero-Trust Security & Boundary Safety): Scope guards, session isolation, and error boundaries are verified. Zero privilege escalation risks.
    • Criterion 3 (Modularity & Clean Architecture): Clean separation of concerns without contributing to file bloat, monolithic sprawl, or circular imports.
    • Criterion 4 (Quality Gates & Test Evidence): deno fmt, deno task lint, deno task check, and deno test --allow-all pass with 0 errors/warnings. Comprehensive test coverage for happy and failure paths.
    • Criterion 5 (Runtime & Client-Side Integrity): For UI changes, zero runtime JS parsing/syntax errors (validated via ui/ui_scripts.test.ts), accessible layout, and consistent styling tokens.
  4. Output the Standard Code Audit Report:
    • Overall Implementation Score: [e.g. 5/5, 4/5, or Letter Grade]
    • Verdict: [MERGE READY / REVISION REQUIRED / BLOCKED]
    • Successes & Verified Achievements: Verified working features with evidence.
    • Deficiencies, Regressions & Failure Risks: Bugs, unhandled errors, UX regressions, or security gaps found.
    • Actionable Remediation Suggestions: Specific, prioritized code changes needed before release.

2. Dispatch Template (When Preparing a Prompt for Jules or External Agents)

When commanded to "Prepare an Audit-2 prompt for Jules", fill in and provide the following block:

**Role:** Act as a Senior Security, Architecture & Quality Assurance Auditor. Do not modify production code or push commits during this audit session. Your sole deliverable is an objective Code Quality & Security Audit Report.

**The Scope:** [Specify target branch, recent commits, modified files, or task in `tasks/new/TASK_FILENAME.md` or `tasks/complete/TASK_FILENAME.md`].

**Your Task:**
Audit the actual codebase changes against the original task specification and our system guidelines (`AGENTS.md`, `docs/`) using the 5-point implementation rubric in `tasks/audit-2.md`:
1. Specification & Scope Fidelity
2. Zero-Trust Security & Boundary Safety
3. Modularity & Clean Architecture
4. Quality Gates & Test Evidence
5. Runtime & Client-Side Integrity

**Deliverable:**
Provide a structured code audit report with:
- **Overall Implementation Score:** [e.g. 5/5, 4/5, or Letter Grade]
- **Verdict:** [MERGE READY / REVISION REQUIRED / BLOCKED]
- **Successes & Verified Achievements:** Exact functionality verified and working as expected.
- **Deficiencies, Regressions & Failure Risks:** Technical bugs, unhandled errors, UX regressions, or security gaps found.
- **Actionable Remediation Suggestions:** Specific, prioritized code fixes or refactoring steps needed before final approval.