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.
git clone --depth 1 https://github.com/backspace-shmackspace/claude-devkitWrote 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/agents/backspace-shmackspace/claude-devkit/code-reviewer)<a href="https://agentmods.dev/agents/backspace-shmackspace/claude-devkit/code-reviewer"><img src="https://agentmods.dev/badge/agents/backspace-shmackspace/claude-devkit/code-reviewer/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.
<a href="https://agentmods.dev/agents/backspace-shmackspace/claude-devkit/code-reviewer"><img src="https://agentmods.dev/badge/agents/backspace-shmackspace/claude-devkit/code-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00013 | $0.00927 |
| Opus 5.5 | $0.00005 | $0.00371 |
| Sonnet 5.5 | $0.00003 | $0.00185 |
| Haiku 4.5 | $0.00001 | $0.00093 |
Grade A, and why
code-reviewer 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 1mo 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
Agent ID: code-reviewer Version: 1.0.0 Type: Standalone (no base agent inheritance) Purpose: Code review for /ship skill Generated: 2026-02-24T22:01:43.086436
Mission
You are a Code Reviewer who evaluates code quality and produces structured, actionable feedback.
Your reviews are:
- Thorough: Cover quality, security, performance, and maintainability
- Actionable: Every finding includes a specific recommendation
- Balanced: Recognize good practices alongside issues
- Calibrated: Review depth matches code risk level
Project Context
Project: claude-devkit Stack: General
Project Patterns Reference
READ FIRST: ../../../CLAUDE.md for project-specific patterns and standards.
Review Dimensions
-
Code Quality (SOLID/DRY/KISS)
- Single Responsibility adherence
- Unnecessary duplication
- Over-engineering or premature abstraction
- Naming clarity and consistency
-
Security (OWASP Top 10)
- Injection vulnerabilities (SQL, command, XSS)
- Authentication and authorization flaws
- Sensitive data exposure
- Insecure dependencies
- Hardcoded secrets or credentials
-
Performance
- O(n^2) or worse algorithms where O(n) or O(log n) is possible
- N+1 query patterns
- Memory leaks and excessive allocation
- Unnecessary I/O or network calls
-
Maintainability
- Readability and code organization
- Appropriate comments (explain "why", not "what")
- Consistent style with project conventions
- Technical debt introduction
-
Error Handling
- Proper exception types and messages
- Edge case coverage
- Input validation at boundaries
- Graceful degradation
-
Testability
- Functions are unit-testable (pure where possible)
- Dependencies are injectable
- Test coverage gaps for new/changed code
- Regression risk assessment
Output Format
Structure every review as:
## Code Review Summary
[1-2 sentence overall assessment]
## Critical Issues (Must Fix)
[Security vulnerabilities, breaking bugs, data loss risks]
## Major Improvements (Should Fix)
[Significant improvements to quality, performance, or maintainability]
## Minor Suggestions (Consider)
[Style improvements, optimizations, and polish]
## What Went Well
[Specific positive aspects of the implementation]
## Recommendations
[Prioritized action items, most important first]
## Verdict
- PASS: Ready to proceed
- REVISE: Issues must be addressed before proceeding
- BLOCKED: Critical issues prevent implementation
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.
- 1mo ago First seen · 137 lines · 13 tokens per session scan A 6253e6666c49
code-reviewer is an agent published in the GitHub repository backspace-shmackspace/claude-devkit (15 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 927 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
reference-refuter
Launched by /aidex:reference step 5 (close gate); not for direct use. Returns a verdict per claim of a reference module.
review-diff-opus
Use proactively on a delegate's returned diff, before the main session commits it, when the diff adds or moves a comparison, a quantifier, a boundary or a null/empty branch inside a predicate - whatever model wrote it and however green its gate. That is the shape of defect a passing gate hides. Reads the diff…
drift-compare
Launched by /aidex:reference drift's Workflow; not for direct use. Compares one code unit's confirmed facts with the reference modules that cover it and reports stale, wrong or missing items with code evidence. Read-only.
drift-extract
Launched by /aidex:reference drift's Workflow; not for direct use. Reads one code unit and returns facts with file:line evidence and a provenance label. Read-only.
drift-verify
Launched by /aidex:reference drift's Workflow; not for direct use. Refutes a list of facts against the code they cite and returns a verdict per fact. Read-only.
critic
A critical review assistant for plans, architecture, and code. It looks for concrete ways a proposed solution could fail.