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.
npx agentmods add skills/backspace-shmackspace/claude-devkit/ai-code-reviewnpx skills add backspace-shmackspace/claude-devkit --skill ai-code-reviewgit 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/skills/backspace-shmackspace/claude-devkit/ai-code-review)<a href="https://agentmods.dev/skills/backspace-shmackspace/claude-devkit/ai-code-review"><img src="https://agentmods.dev/badge/skills/backspace-shmackspace/claude-devkit/ai-code-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 | $0.00053 | $0.01902 |
| Opus 5 | $0.00026 | $0.00951 |
| Sonnet 5 | $0.00011 | $0.00380 |
| Haiku 4.5 | $0.00005 | $0.00190 |
Grade A, and why
ai-code-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 4d 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.
This is a copy
89% identical to ai-code-review — 29 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Generated Code Security Review
Security review checklist and methodology for code produced by AI coding assistants (Claude, Copilot, Cursor, Gemini, or any LLM-based tool). AI-generated code has characteristic failure modes that differ from human-written code and require specific review attention.
When to Use
- Reviewing PRs or patches marked with
Assisted-by:orGenerated-by:attribution - Auditing code known or suspected to be AI-generated
- As a supplementary checklist during any code review where AI assistance was used
- Verifying AI-generated security fixes or test code
When NOT to Use
- General code review without AI involvement (use
module/skills/differential-review/SKILL.md) - Reviewing AI model behavior or prompt injection (use
module/skills/prompt-injection-mitigation/SKILL.md) - Evaluating AI tool security posture (use
module/skills/third-party-model-security/SKILL.mdormodule/skills/file-protection/SKILL.md)
AI-Specific Failure Modes
AI code generation has characteristic error patterns that differ from typical human mistakes. Review for these specifically:
1. Hallucinated APIs and symbols
LLMs confidently generate calls to functions, methods, flags, configuration keys, or library features that do not exist. These compile or parse correctly but fail at runtime, or worse, silently do nothing.
Detection:
- Verify every imported module, function call, and configuration key against the actual codebase and library documentation
- Check that method signatures match (argument count, types, return values)
- Search the project for the symbol:
rg "function_name"— if it only appears in the new code, it may be hallucinated - Check library version: AI may reference APIs from a different version than what the project uses
Security impact: A hallucinated security function (e.g., a
nonexistent sanitize_input() call) provides zero protection
while giving the appearance of safety.
2. Plausible-but-wrong logic
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.
- 4d ago First seen · 229 lines · 53 tokens per session scan A 04ecac7c13b8
ai-code-review is a skill published in the GitHub repository backspace-shmackspace/claude-devkit (15 stars, last pushed 10d ago), licensed MIT. It adds 53 tokens to every session and 1,902 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to ai-code-review, differing in 29 lines, and is treated as a copy.
Other skills, from other repositories
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.
merge-strategy
Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
ap-juror
L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.