cognitive_robot_abstract_machine: Skill for Claude Code

.claude/skills/local-code-review/SKILL.md

local-code-review is a skill for Claude Code from cram2/cognitive_robot_abstract_machine. It costs 71 tokens per session (2,728 once invoked), scanned B, original, LGPL-3.0.

A local code-review workflow that compares the current branch with cram2's upstream main branch. It checks for bugs and compliance with AGENTS.md, the project's contributor instructions, then plans fixes and missing tests.

In plain words
What is it for?
Use it to review a branch against the main codebase and prepare fixes for bugs, instruction violations, and insufficient test coverage.
Why use it?
It helps find problems before changes are pushed or submitted for review.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is cram2/cognitive_robot_abstract_machine's own configuration. It tells Claude Code how to work on cognitive_robot_abstract_machine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cognitive_robot_abstract_machine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cram2/cognitive_robot_abstract_machine. 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/cram2/cognitive_robot_abstract_machine/main/.claude/skills/local-code-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cram2/cognitive_robot_abstract_machine

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.

agentmods badge for local-code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/cram2/cognitive_robot_abstract_machine/local-code-review.svg)](https://agentmods.dev/skills/cram2/cognitive_robot_abstract_machine/local-code-review)
Your own site
<a href="https://agentmods.dev/skills/cram2/cognitive_robot_abstract_machine/local-code-review"><img src="https://agentmods.dev/badge/skills/cram2/cognitive_robot_abstract_machine/local-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,728 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 5.1 $0.00071 $0.02728
Opus 5 $0.00036 $0.01364
Sonnet 5 $0.00014 $0.00546
Haiku 4.5 $0.00007 $0.00273

Measured 8d ago against content hash 3bd631b3a5a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

local-code-review scanned grade B with 1 finding 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **To find the current report at any later step, or after a context compaction**, read `.claude/claude_reviews/.active` to get the path, then open that report. Never guess, and never read the other (stale) reports in th
.claude/skills/local-code-review/SKILL.md · 122 lines

The source is not reproduced here

Licensed LGPL-3.0

The repository is licensed LGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 8d ago First seen · 122 lines · 71 tokens per session scan B 3bd631b3a5a8

Subscribe to this mod's changes

local-code-review is a skill published in the GitHub repository cram2/cognitive_robot_abstract_machine (21 stars, last pushed 3d ago), licensed LGPL-3.0. It adds 71 tokens to every session and 2,728 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.