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 skills add nortonx/ai-tooling-free --skill fanout-reviewgit clone --depth 1 https://github.com/nortonx/ai-tooling-freeWrote 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/nortonx/ai-tooling-free/fanout-review)<a href="https://agentmods.dev/skills/nortonx/ai-tooling-free/fanout-review"><img src="https://agentmods.dev/badge/skills/nortonx/ai-tooling-free/fanout-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/skills/nortonx/ai-tooling-free/fanout-review"><img src="https://agentmods.dev/badge/skills/nortonx/ai-tooling-free/fanout-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 | $0.00063 | $0.03925 |
| Opus 5.5 | $0.00025 | $0.01570 |
| Sonnet 5.5 | $0.00013 | $0.00785 |
| Haiku 4.5 | $0.00006 | $0.00392 |
Grade A, and why
fanout-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 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code review (multi-perspective)
Review the current branch by dispatching 6 parallel review tasks (one mandate each), then synthesize findings into a categorical merge-gate decision (🚫 BLOCK / ⚠️ NEEDS DISCUSSION / ✅ CLEAR) backed by a risk profile and deterministic blocker checks. Output is designed to paste directly into a PR thread (GitHub, GitLab, or Azure DevOps).
Mode detection
Read the user invocation prompt:
- Contains
quick,shallow, orfast-> single-pass mode (skip fanout, lean output) - Diff size below ~50 lines AND mode not explicitly stated -> ask the user once whether to do single-pass; default to single-pass if unanswered
- Otherwise -> fanout mode (default)
Scope detection
Read the user invocation prompt:
- Mentions
committed,this branch,PR, ormain..HEAD-> scope to committed changes only (git diff main..HEAD) - Mentions
staged-> scope togit diff --cached - Otherwise -> include all changes (committed + staged + unstaged)
Base branch resolution, in order:
- If the user prompt names a branch (
vs feat/X,against develop), use it. - Else
git symbolic-ref refs/remotes/origin/HEADif it resolves. - Else
mainif it exists locally, elsemaster. - If neither exists, stop and ask the user which base to diff against. Do not silently fall back to
HEAD~1.
Fanout mode
Step 1: Gather diff context
Run (substitute scope from detection above):
git diff <scope> --stat
git diff <scope> --name-status
git log <scope> --no-merges --pretty=format:"%h %s"
Step 2: Dispatch 6 review tasks
Dispatch the review across 6 independent perspectives.
Multi-runtime execution guidelines:
- Claude Code: Use the
Agenttool withsubagent_type: general-purpose. Send all 6 tasks in a single turn with 6 tool calls for concurrent execution. - Antigravity / Gemini CLI: Use
invoke_subagentwith 6 parallel entries in theSubagentsarray. - Single-agent runtimes (such as GitHub Copilot CLI): When parallel subagents are unavailable, evaluate each of the 6 review perspectives sequentially, accumulating JSON findings into context.
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 Changed · +7 lines · +1 tokens per session 4d58627abd12
- 1mo ago First seen · 278 lines · 62 tokens per session scan A ad9992338576
fanout-review is a skill published in the GitHub repository nortonx/ai-tooling-free (1 stars, last pushed 18d ago), licensed MIT. It adds 63 tokens to every session and 3,925 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
adapter-audit
Use this skill to audit CLI adapter projects (like opencli) for missing output fields, then batch-generate fixes and submit PRs. Turns AI agents into adapter quality reviewers.
security-audit
Deep adversarial security audit engine for full-stack web applications. Use this skill when the user wants to audit a codebase for security vulnerabilities, broken access control, injection risks, authentication weaknesses, payment security, file upload exploits, IDOR, CSRF, SSRF, RLS bypass, business logic abuse…
roblox-code-review
Use to review Luau / Roblox code for server-authority holes, anti-slop violations, replication mistakes, and Roblox-specific bugs before merge. Use when the user says "review this code", "code review", "review the PR", "audit this script", "is this server-safe", or after roblox-forge ships a non-trivial change.
roblox-anti-slop
Use to strip enterprise jargon (Controller, Service-as-non-engine-service, Repository, DTO, Manager, Handler) out of Luau code and rewrite it as Roblox-native. Use when reviewing generated code that looks like Java enterprise architecture, when the user complains it doesn't "feel like Roblox", or as a final pass after…
spec-kitty-runtime-review
Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…
adversarial-squad
Deploy a bounded, profile-loaded adversarial review squad at an SDD point-cut (post-spec, post-plan, post-tasks, pre-merge, or an ad-hoc decision) so independent doctrine lenses converge on findings one reviewer would miss. Triggers: "deploy a squad", "adversarial squad", "post-tasks anti-laziness pass", "pre-spec…