integrity

A command for a quick integrity audit of recent work, examining what could make the main result or claim invalid.

In plain words
What is it for?
Use it after recent commits or staged changes to list and rank risks, along with whether each has been checked.
Why use it?
It surfaces unchecked assumptions, missing evidence, self-deception risks, and procedures followed without a clear reason.

Command for Claude Code

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 commands/cdeust/ai-architect-mcp-codebase/integrity
Clone the repo
git clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebase

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 210 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00210
Opus 5 $0.00000 $0.00105
Sonnet 5 $0.00000 $0.00042
Haiku 4.5 $0.00000 $0.00021

Measured 2d ago against content hash 7079215296b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

integrity 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 2d ago.

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.

.claude/commands/zetetic/integrity.md · 30 lines

What it actually says

Quick Integrity Audit

Fast integrity check on the current work. Feynman-style: what could invalidate this?

Instructions

  1. Look at the recent work in this session (recent commits, staged changes, or $ARGUMENTS if provided).

  2. For the main claim/result/change, list 3-5 things that could invalidate it, ranked by damage.

  3. For each: is there evidence for or against it? Has it been checked?

  4. Self-deception check: is the team invested in this being true? What procedural check would catch bias?

  5. Cargo-cult check: is any procedure being followed "because successful teams do it" without the causal mechanism?

  6. Present as:

    Quick Integrity Audit
    
    What could invalidate this:
    1. [highest damage] — checked: [yes/no]
    2. ...
    
    Self-deception risk: [high/medium/low]
    Cargo cult candidates: [list or none]
    

$ARGUMENTS

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.

  1. 2d ago First seen · 30 lines · 0 tokens per session scan A 7079215296b8

Subscribe to this mod's changes

integrity is a command published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 210 tokens. 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.