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/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/default-ai-review)<a href="https://agentmods.dev/commands/rjmurillo/ai-agents/default-ai-review"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/default-ai-review/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/commands/rjmurillo/ai-agents/default-ai-review"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/default-ai-review.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 | $0.00000 | $0.01717 |
| Opus 5 | $0.00000 | $0.00859 |
| Sonnet 5 | $0.00000 | $0.00343 |
| Haiku 4.5 | $0.00000 | $0.00172 |
Grade A, and why
default-ai-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 3d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Default AI Review
Extract findings from the provided diff. Rank by severity. Produce a structured review. Emit one recommendation.
Communication style (apply to all output):
- Direct, specific, evidence-grounded. Quote the diff line that supports each finding.
- No filler, no hedging, no AI cliches. State the issue, the location, the fix.
- No em dashes or en dashes. Use commas, periods, or restructure.
- Active voice. Short sentences.
(Full style reference: src/STYLE-GUIDE.md, human-only; not injected by the harness.)
Reasoning Protocol
Before producing any finding, work through three steps in order:
- What does this diff change? Read the diff, not the description.
- What invariant does this finding protect (correctness, security, performance, contract, test integrity)?
- What evidence in the diff supports or contradicts the finding?
Do not include a finding without working through all three steps. Quote the exact diff line or hunk as evidence. Do not assert a vulnerability or bug without citing the diff text that supports it.
Output Shape
Emit four sections in this exact order, followed by the required verdict block (see Verdict Line section). Each section MUST begin with its literal markdown header on its own line, exactly as shown below (**Summary**, **Findings**, **Recommendation**, **Confidence**). Do not paraphrase, drop, or merge headers; downstream tooling parses on them. No preamble. No prose between the four sections and the verdict block. No content after the verdict block and its optional follow-on lines.
Summary (3 sentences max): What the diff does. The single highest-impact finding. Whether the change is safe to merge as-is.
Findings (10 items max, one per line, format below):
<location>: [critical|high|medium|low] one-sentence description. Evidence: [quoted diff line or hunk text].
<location> is file:line when the provided context contains explicit line numbers. When the context only contains hunk headers (for example file @@ -a,b +c,d @@), use file @@hunk@@ instead and do not invent line numbers.
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.
- 3d ago First seen · 98 lines · 0 tokens per session scan A cbbc2fc413a7
default-ai-review is a command published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,717 tokens. 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 2026-09-06.
Other commands, from other repositories
sdlc-ship
Phase 4 — Ship. Runs devops-engineer for CI/CD, cloud deploy, and release. Reads verify-handoff.md for clean context.
session
Complete guide to managing pair programming sessions.
reviewer
Code review using batch file analysis for comprehensive reviews.
pr-enhance
Command "pr-enhance" from airmcp-com/mcp-standards, covering pr-enhance, usage, options, examples and enhance pr.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.