Borrowing it
Nothing to install: this file belongs to berekvolgyipeter/dotclaude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/berekvolgyipeter/dotclaude/main/.claude/commands/consistency-review.mdgit clone --depth 1 https://github.com/berekvolgyipeter/dotclaudeWrote 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.
[](https://agentmods.dev/commands/berekvolgyipeter/dotclaude/consistency-review)<a href="https://agentmods.dev/commands/berekvolgyipeter/dotclaude/consistency-review"><img src="https://agentmods.dev/badge/commands/berekvolgyipeter/dotclaude/consistency-review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00022 | $0.01130 |
| Opus 5 | $0.00011 | $0.00565 |
| Sonnet 5 | $0.00004 | $0.00226 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
consistency-review 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
!bash ~/.claude/scripts/review/delta-diff.sh
The overview above lists the changed files and stats — not the diffs themselves. For each changed file, read its diff on demand with git diff HEAD -- <file> (read untracked files directly). Review those changes for consistency with this repo (dotclaude): not functional bugs, but alignment with its documented conventions, structure, and engineering philosophy.
Load the source of truth
Read these before judging — quote the specific rule you're checking against, never paraphrase from memory:
.claude/CLAUDE.md— the Rules for Changes and Engineering Philosophy sections.README.mdandshared/rules-index.md— to check whether they are in sync with the change.- For each changed file, read the file and its neighbors (sibling entries, surrounding lines) to judge whether the new content matches their style.
Checks
Work through each. For every finding, cite file:line, quote the rule it breaks, and give the fix.
1. Repo conventions (.claude/CLAUDE.md → Rules for Changes)
- README sync — was
README.mdupdated for every added/removed/changed rule, command, skill, agent, hook, output style, template, or script? - Command frontmatter — does every new or changed command file carry
disable-model-invocation: true? - Rules index sync — was
shared/rules-index.mdupdated when a rule or context-rule file was added or removed? - Context-rule placement — do on-demand rule files live in
context-rules/(notrules/) and have their glob registered inload-context-rules.sh? - Source acknowledgment — if content was drawn from a
plugin-browsersource, is the repo listed under README Acknowledgments? - Script placement — are hook scripts in
hooks/and helper scripts inscripts/? - No irrelevant cross-references / no leaked internals — is every artifact named one the reader actually reads, applies, or invokes? Is every env var, flag, or script detail one the reader actually sets or reacts to?
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.
- 7d ago First seen · 73 lines · 22 tokens per session scan A 51200ae4e236
consistency-review is a command published in the GitHub repository berekvolgyipeter/dotclaude (2 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,130 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.
Other commands, from other repositories
review-branch
Review an existing branch holistically before merging — blast radius, conventions, security, and spec compliance.
architecture-scenario-explorer
Explore architectural decisions through systematic scenario analysis with trade-off evaluation and future-proofing assessment.
code-permutation-tester
Test multiple code variations through simulation before implementation with quality gates and performance prediction.
code-to-task
Command "code-to-task" from qdhenry/Claude-Command-Suite, covering convert code analysis to linear tasks, purpose, usage, scan entire codebase for todos and create tasks and scan specific directory or module.
parallel-feature-build
Orchestrated parallel implementation of complex features using multiple agents, with dependency-aware batching and synchronized progress tracking.
rust:audit-clean-arch
Comprehensive audit of Rust codebase against Clean Architecture principles, identifying violations and improvement opportunities.