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 AgentBuildersApp/eight-eyes --skill 8eyesgit clone --depth 1 https://github.com/AgentBuildersApp/eight-eyesWrote 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/agentbuildersapp/eight-eyes/8eyes)<a href="https://agentmods.dev/skills/agentbuildersapp/eight-eyes/8eyes"><img src="https://agentmods.dev/badge/skills/agentbuildersapp/eight-eyes/8eyes/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/agentbuildersapp/eight-eyes/8eyes"><img src="https://agentmods.dev/badge/skills/agentbuildersapp/eight-eyes/8eyes.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 | $0.00015 | $0.01655 |
| Opus 5 | $0.00008 | $0.00827 |
| Sonnet 5 | $0.00003 | $0.00331 |
| Haiku 4.5 | $0.00002 | $0.00166 |
Grade A, and why
8eyes 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 8d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/8eyes - Multi-Agent Code Review
Trigger: /8eyes [target]
Version: 4.2.0 — Verifiable Enforcement (installed plugin version)
Overview
Eight constrained reviewer roles with hook-enforced isolation. Prevents AI reviewer consensus failure through architectural enforcement.
Roles
| Role | Focus | GLM 5.1 Eligible? | Kimi K2.6 Eligible? |
|---|---|---|---|
| Implementer | Code correctness, logic | YES (alt — opt-in) | NO (default vendor stays) |
| Test Writer | Test coverage, edge cases | YES (alt — opt-in) | NO (default vendor stays) |
| Skeptic | Adversarial review, assumptions | NO (MiniMax canonical Skeptic) | NO (MiniMax canonical Skeptic) |
| Security | Vulnerabilities, auth, secrets | NO — HARD EXCLUSION | NO — HARD EXCLUSION |
| Performance | Bottlenecks, complexity | NO (default vendor stays) | NO (default vendor stays) |
| Accessibility | WCAG compliance, UX | NO (default vendor stays) | NO (default vendor stays) |
| Docs | Documentation completeness | NO (default vendor stays) | NO (default vendor stays) |
| Verifier | Final sign-off, integration | NO (default vendor stays) | NO (default vendor stays) |
| Long-Context Reviewer (opt-in) | Cross-file architectural review when target spans 5-15 files | YES — GLM 200K context lane | YES — Kimi long-horizon lane |
| Architect-alt (opt-in) | Cross-module architectural reasoning, large-design review | NO (default vendor stays) | YES — Kimi long-context architect lane |
Min-1-Eastern Requirement (VON-1408 P2)
When invoking /8eyes by default (no operator-supplied --role overrides), at least 1 of the 8
default reviewer roles MUST be filled by an Eastern model (Kimi, MiniMax, or GLM), unless the
governance-locked hard exclusions apply (see below). This requirement is satisfied automatically
because MiniMax already canonically fills the Skeptic role; the requirement only forces visible
review when an operator attempts to override the default skeptic with a Western model.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 133 lines · 15 tokens per session scan A 1737851e910b
8eyes is a skill published in the GitHub repository AgentBuildersApp/eight-eyes (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,655 once invoked, about $0.0001 per session on Opus 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
Independent Review Synthesis
A review tool that combines findings from multiple human or AI code reviews and checks them against the diff, surrounding code, tests, and prior findings.
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
review-team
A multi-reviewer code review process that checks a change from several specialist viewpoints and combines the results into one report. It can cover bugs, security, tests, dependencies, frontend behavior, and continuous-integration workflows.
typescript-quality-enforcer
Audit and strengthen TypeScript/JavaScript type-evidence and lint discipline, stage adoption of deterministic anti-slop Oxlint rules, and remediate approved violations without laundering diagnostics. Use when a repository needs stronger TypeScript/JavaScript quality enforcement, unsafe type escape-hatch cleanup…
grok-build-delegate
Use the local Grok Build CLI for second-opinion reviews, adversarial critiques, or delegated read-only investigation from Codex.
Review Comment Triage (No-Code-Fix Mode)
A review workflow for sorting existing pull-request comments by severity, status, and next action without changing the code.