audit

Stars10

Forks2

UpdatedJune 7, 2026 at 21:39

Strictly verifies the codebase against a specific MiniPRD and reconciles the Hypergraph memory.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Source

tjmustard

tjmustard/OIN-SMILES

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

Software Quality Assurance Analysts and TestersComputer and Mathematical Occupations·SOC 15-1253

SKILL.md

readonly

name	audit
description	Strictly verifies the codebase against a specific MiniPRD and reconciles the Hypergraph memory.
trigger	/hyper-audit [Path to MiniPRD]

ROLE: The Auditor Agent

Your objective is to verify newly written code against its strict requirements and sequentially reconcile the system's YAML memory graph.

INPUTS

The target MiniPRD.md (Provided via slash command argument).
The spec/compiled/architecture.yml hypergraph file.
The specific source code files recently modified by the Builder Agent.

CRITICAL RULES

No Scope Creep: Evaluate code STRICTLY against the Acceptance Criteria and Negative Space in the MiniPRD.md. Do not suggest stylistic refactors outside of this scope.
Fresh Context: Read the source code directly from the disk. Do not rely on conversational memory.

STATE MACHINE PHASES

[PHASE 1: Contract Verification]

Action: Analyze the modified code against the MiniPRD.
Output: If it fails, generate an actionable Punch List, return it to the Builder, and HALT execution. If it passes, output [VERIFICATION: PASSED].

[PHASE 2: Test Validation]

Action: Verify Deterministic Tests pass. If Novel Tests were run, verify a human-approved output exists in tests/fixtures/.
Output: Pass/Fail. If fail, HALT and return to Builder.

[PHASE 3: Hypergraph Reconciliation (CRITICAL)]

Trigger: Phases 1 and 2 passed.
Action: Launch a Haiku sub-agent to perform the mechanical YAML reconciliation:
- Use the Agent tool with subagent_type: "general-purpose" and model: "haiku"
- Prompt the sub-agent: "Read spec/compiled/architecture.yml. Find every node with status: needs_review. For each such node: (1) Read the file at its associated_file path. (2) Analyze the file's actual inputs, outputs, and purpose from the code. (3) Rewrite the node's inputs, outputs, and description fields to accurately reflect what the implementation actually does. (4) Change status from needs_review to clean. Write the updated architecture.yml when all nodes are processed. Return a list of every node ID you updated with a one-sentence summary of what changed for each."
- Wait for the sub-agent to complete and return the updated architecture file.
- Fallback: If the sub-agent fails or returns an error, reconcile the YAML manually in the main context using the same instructions above.
Output: Report the nodes reconciled and their changes. Output [AUDIT COMPLETE & HYPERGRAPH RECONCILED].

[PHASE 4: MiniPRD Archival]

Trigger: Phase 3 passed.
Action:
1. Move the audited MiniPRD_*.md from spec/compiled/ to spec/archive/:
```
mv spec/compiled/MiniPRD_[Target].md spec/archive/MiniPRD_[Target]_AUDITED.md
```
2. This removes the completed MiniPRD from the active compiled directory so it does not surface in future /hyper-execute runs. spec/archive/ is blocked from agent context via .agentignore.
Output: Confirm the file was moved. Output [MINIPRD ARCHIVED]. Inform the user the feature loop is complete.

More from this repository

same repository

hyper-document

tjmustard/OIN-SMILES

Updates all project documentation after code or skill changes. Always reads actual implementation before writing. Covers README, CHANGELOG, docs/, AGENTS.md, memory files, and skills-info.md. Use after completing any feature, fix, refactor, or skill update.

2026-07-2710

handoff

tjmustard/OIN-SMILES

Compacts the current conversation into a handoff document so a fresh agent can continue the work. Saves to the OS temp directory, not the workspace. Pass an optional argument describing what the next session will focus on.

2026-07-2510

process-document

tjmustard/OIN-SMILES

Documents the process, methodology, and decisions of the current session as a reproducible narrative. Saves to spec/process/ in the workspace so the journey can be understood and recreated by others.

2026-07-2510

hyper-init

tjmustard/OIN-SMILES

Scaffolds a new project by conducting an interview to collect metadata and generating standard repository documentation files from the framework templates. Use when setting up a new repository.

2026-07-0310

hyper-tutorial-audit

tjmustard/OIN-SMILES

Run this after /hyper-tutorial-run to turn tutorial failures into a structured, constraint-aware goal prompt. Interviews the user about their goal and what may/may not be changed, then generates a paste-ready prompt for a new Claude Code fix session. Does NOT re-run tutorial commands.

2026-07-0310

tutorial-generator

tjmustard/OIN-SMILES

Generates a markdown tutorial from an integration test or user-provided files through iterative LLM + human collaboration. Tutorials are saved to tutorials/<name>/ with organized supporting files.

2026-07-0310

ROLE: The Auditor Agent

Your objective is to verify newly written code against its strict requirements and sequentially reconcile the system's YAML memory graph.

INPUTS

The target MiniPRD.md (Provided via slash command argument).

The spec/compiled/architecture.yml hypergraph file.

The specific source code files recently modified by the Builder Agent.

CRITICAL RULES

No Scope Creep: Evaluate code STRICTLY against the Acceptance Criteria and Negative Space in the MiniPRD.md. Do not suggest stylistic refactors outside of this scope.

Fresh Context: Read the source code directly from the disk. Do not rely on conversational memory.

STATE MACHINE PHASES

[PHASE 1: Contract Verification]

Action: Analyze the modified code against the MiniPRD.

Output: If it fails, generate an actionable Punch List, return it to the Builder, and HALT execution. If it passes, output [VERIFICATION: PASSED].

[PHASE 2: Test Validation]

Action: Verify Deterministic Tests pass. If Novel Tests were run, verify a human-approved output exists in tests/fixtures/.

Output: Pass/Fail. If fail, HALT and return to Builder.

[PHASE 3: Hypergraph Reconciliation (CRITICAL)]

Trigger: Phases 1 and 2 passed.

Action: Launch a Haiku sub-agent to perform the mechanical YAML reconciliation:

Use the Agent tool with subagent_type: "general-purpose" and model: "haiku"
Prompt the sub-agent: "Read spec/compiled/architecture.yml. Find every node with status: needs_review. For each such node: (1) Read the file at its associated_file path. (2) Analyze the file's actual inputs, outputs, and purpose from the code. (3) Rewrite the node's inputs, outputs, and description fields to accurately reflect what the implementation actually does. (4) Change status from needs_review to clean. Write the updated architecture.yml when all nodes are processed. Return a list of every node ID you updated with a one-sentence summary of what changed for each."
Wait for the sub-agent to complete and return the updated architecture file.
Fallback: If the sub-agent fails or returns an error, reconcile the YAML manually in the main context using the same instructions above.

Output: Report the nodes reconciled and their changes. Output [AUDIT COMPLETE & HYPERGRAPH RECONCILED].

[PHASE 4: MiniPRD Archival]

Trigger: Phase 3 passed.

Action:

Move the audited MiniPRD_*.md from spec/compiled/ to spec/archive/:

mv spec/compiled/MiniPRD_[Target].md spec/archive/MiniPRD_[Target]_AUDITED.md

This removes the completed MiniPRD from the active compiled directory so it does not surface in future /hyper-execute runs. spec/archive/ is blocked from agent context via .agentignore.

Output: Confirm the file was moved. Output [MINIPRD ARCHIVED]. Inform the user the feature loop is complete.