What is consistency-check?

A read-only command that checks whether project memory, rules, agent descriptions, decisions, and related records agree with one another.

Use it to run all enabled checks or select one with --check; it can also narrow staleness checks with --since.

It finds semantic drift and broken references that ordinary deterministic lint checks may miss, without applying changes.

How jaroslavsoucek-art/Giovanni configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jaroslavsoucek-art/Giovanni. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jaroslavsoucek-art/Giovanni/main/.claude/commands/consistency-check.md

Clone the repo

git clone --depth 1 https://github.com/jaroslavsoucek-art/Giovanni

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jaroslavsoucek-art/giovanni/consistency-check/github.svg)](https://agentmods.dev/commands/jaroslavsoucek-art/giovanni/consistency-check)

Your own site

<a href="https://agentmods.dev/commands/jaroslavsoucek-art/giovanni/consistency-check"><img src="https://agentmods.dev/badge/commands/jaroslavsoucek-art/giovanni/consistency-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/jaroslavsoucek-art/giovanni/consistency-check"><img src="https://agentmods.dev/badge/commands/jaroslavsoucek-art/giovanni/consistency-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,820 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00052	$0.01820
Opus 5	$0.00026	$0.00910
Sonnet 5	$0.00010	$0.00364
Haiku 4.5	$0.00005	$0.00182

Measured today against content hash 42e04024f592, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

consistency-check 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 today.

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/consistency-check.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/consistency-check

Run the 8 semantic invariants that deterministic scripts/lint.sh cannot reach (memory↔constitution drift, decisions↔constitution drift, agent roster description mismatch, topic shard cross-reference breakage, optional architecture audit staleness, decided-terms completeness, knowledge↔knowledge cross-doc drift, published-pages outbound drift). This command is a thin shell — checks and report format live in the consistency-checker agent. This file is the invocation contract.

Usage

/consistency-check                          # all enabled checks
/consistency-check --check <id>             # single check
/consistency-check --since <YYYY-MM-DD>     # narrows git-log scan window for staleness checks
/consistency-check --write                  # commit findings to file (default = also writes; flag is reserved for future render-only mode)

Valid --check ids:

memory-blockers-vs-constitution
decisions-vs-constitution
agent-roster-semantic
topic-shard-stakeholder-xref
audit-staleness (optional — only if fork uses architecture tier audits)
decided-terms-completeness (no-op with INFO if memory/audits/consistency/decided-terms.yaml is absent)

Argument syntax

Arg	Type	Default	Meaning
`--check <id>`	parameterized	all	Run a single check by ID instead of all enabled checks.
`--since <YYYY-MM-DD>`	parameterized date	30 days ago	For staleness check (`audit-staleness`): limits the git-log window. Ignored by other checks.
`--write`	boolean flag	implicit (always writes report)	Reserved for future render-only mode. Default behavior writes the report file.

Pre-flight (binding — STOP on failure)

Before spawning consistency-checker:

CWD check. Working directory is a Giovanni repo (presence of memory/CLAUDE_MEMORY.md + knowledge/<constitution>.md). Otherwise STOP.
Agent definition present. .claude/agents/consistency-checker.md exists. Missing → STOP.
Audit directory present. memory/audits/consistency/ exists. Create if missing (this is the only directory the orchestrator creates pre-spawn).
State file present. memory/audits/consistency/_state.md exists with a non-empty shadow_mode_start_date field. If missing or empty:
- Auto-seed: set shadow_mode_start_date = today, shadow_mode_end_date = today + 28 days.
- Surface advisory: INFO: seeded shadow mode 28d from today. Score precision before promoting to operational warnings.
Constitution + L1 present. knowledge/<constitution_file>.md (per docs/governance.config.yaml) and memory/CLAUDE_MEMORY.md exist. Missing → STOP — the checks have no input.

Read the full file on GitHub · 118 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.

today Changed · +12 tokens per session 42e04024f592
12d ago First seen · 118 lines · 40 tokens per session scan A 778d21c5304a

Subscribe to this mod's changes

consistency-check is a command published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,820 once invoked, about $0.0003 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.

Claude Code Code review agent-framework agentic-ai ai-agents anthropic chief-of-staff

Giovanni: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/consistency-check

Usage

Argument syntax

Pre-flight (binding — STOP on failure)

What this file has done since we first saw it

Other commands, from other repositories

code-review-swarm

pr-manager

sparc-refinement-optimization-mode

reviewer

code-review

pr-enhance