A code-checking workflow that compares recently changed files with a written MiniPRD, a short product requirements document, and updates a YAML record of the system’s structure.

It helps review implementation requirements, create a fix list for failed checks, validate tests, and keep the project’s YAML architecture record current.

It catches missing or extra work against the agreed requirements and checks that tests support the changes before they are accepted.

audit — Skill by tjmustard

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/tjmustard/hypergraph-coding-agent-framework/hyper-audit

Any agent

npx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-audit

Clone the repo

git clone --depth 1 https://github.com/tjmustard/Hypergraph-Coding-Agent-Framework

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 762 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00022	$0.00762
Opus 5	$0.00011	$0.00381
Sonnet 5	$0.00004	$0.00152
Haiku 4.5	$0.00002	$0.00076

Measured yesterday against content hash 527350b6eb7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/hyper-audit/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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].

Read the full file on GitHub · 46 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 46 lines · 22 tokens per session scan A 527350b6eb7d

Subscribe to this mod's changes

audit is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 762 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review Memory and context Testing

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens