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 arcasilesgroup/ai-engineering --skill full-reviewgit clone --depth 1 https://github.com/arcasilesgroup/ai-engineeringWrote 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/arcasilesgroup/ai-engineering/full-review)<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/full-review"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/full-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/arcasilesgroup/ai-engineering/full-review"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/full-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 | $0.00079 | $0.01911 |
| Opus 5.5 | $0.00032 | $0.00764 |
| Sonnet 5.5 | $0.00016 | $0.00382 |
| Haiku 4.5 | $0.00008 | $0.00191 |
Grade A, and why
full-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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full review
Orchestrate all six review skills and merge their output into one report the user can act on top-down. You are the coordinator: you spawn the agents, then reconcile what they return. You do not perform the reviews yourself.
1. Resolve scope once, up front
Determine the scope per .claude/review/CONVENTIONS.md before spawning
anything, and pass the identical scope string to every agent. Agents that each
resolve their own scope will drift apart, and their findings then cannot be
compared or deduplicated.
Detect the stack once here too (per CONVENTIONS.md §1) and pass it down with
the scope. Five agents independently re-deriving the stack is wasted work, and in
a monorepo they can legitimately land on different answers — which silently
produces five reviews of different things.
Also check now whether a design document exists (design.md, docs/design.md,
DESIGN.md, or the project's own spec convention). If none does, do not spawn
the design-check agent — it would halt immediately by design. Note its absence
in the final report instead.
Likewise, if the UI lanes do not apply — a library, a CLI, a backend service with
no interface — skip a11y-audit and say so rather than spawning an agent to
report that there is no UI.
2. Build check first, on its own
Run build-check yourself, synchronously, before the fan-out. It is fast,
objective, and decisive:
- If it FAILS on a compile or type error: stop. Report the failure and ask whether to fix it first or review anyway. Reasoning-based review of code that does not compile is largely wasted — the file is about to change, and half the findings will evaporate with the fix.
- If it fails only on lint: carry on with the fan-out; fold the lint findings into the merged report.
- If it passes: carry on, and pass any size/timing output it produced along to the perf agent so that lane starts from a measurement instead of a guess.
3. Fan out the reasoning reviews
Spawn one general-purpose agent per remaining skill, all in a single message
so they run concurrently:
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 · 164 lines · 79 tokens per session scan A 1d8030933df2
full-review is a skill published in the GitHub repository arcasilesgroup/ai-engineering (61 stars, last pushed 2d ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,911 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 2026-09-12.
Other skills, from other repositories
code-review
Review pull requests for repository fit, meaningful value, trustworthy provenance, differentiation, and maintainability in awesome-copilot.
spec-kitty-mission-review
Review a fully merged Spec Kitty mission post-merge (all WPs done/approved) to verify spec→code fidelity, FR coverage, drift, risks, and security. Triggers: "review the merged mission", "post-merge mission review", "verify the completed mission", "audit the mission implementation", "mission-level acceptance review"…
code-review-csharp
Perform structured code reviews of C# source code covering naming conventions, performance, security, readability, and .NET best practices. Trigger phrases include "review this C# code", "check my C# for best practices", "analyze this C# class", "find issues in my C# code".
mcp-server-review
Review a Model Context Protocol (MCP) server implementation against the 2026-07-28 protocol revision, which removed the initialize handshake and Mcp-Session-Id and made the protocol stateless. Use when the user asks to review, audit, upgrade or migrate an MCP server, asks whether their MCP server is spec compliant…
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…