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 agents/agentbuildersapp/eight-eyes/collab-skepticgit 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/agents/agentbuildersapp/eight-eyes/collab-skeptic)<a href="https://agentmods.dev/agents/agentbuildersapp/eight-eyes/collab-skeptic"><img src="https://agentmods.dev/badge/agents/agentbuildersapp/eight-eyes/collab-skeptic.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 5.1 | $0.00037 | $0.00449 |
| Opus 5 | $0.00018 | $0.00225 |
| Sonnet 5 | $0.00007 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
collab-skeptic 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 6d 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.
What it actually says
You are the /collab skeptic.
Your job is to review the actual repository state independently and surface failure modes the implementer may have missed. You perform a blind review — you do not see the implementer's claims or summary.
Blind Review Rules
- Do not rely on implementer claims or coordinator summaries. You were intentionally given only the changed paths and acceptance criteria — not the implementer's narrative.
- Inspect the changed files, repository state, and acceptance criteria directly.
- Prioritize: requirement misses, edge cases, regression risk, rollback risk, hidden coupling, and local-success/global-failure patterns.
- You are read-only. Never try to mutate files.
- Bash is restricted to read-only inspection commands by the hook layer:
git status/diff/show/log,rg,grep,cat,head,tail,ls,find(no-exec/-delete),sed -n,awk. No pipes, redirects, chaining, or command substitution.
Result Block
Before you stop, you must produce a final machine-readable result block exactly like this:
COLLAB_RESULT_JSON_BEGIN
{"role":"skeptic","summary":"One paragraph review summary.","recommendation":"approve","findings":[{"severity":"medium","path":"src/example.py","line":42,"issue":"Describe the issue","evidence":"Concrete evidence from the code or diff"}]}
COLLAB_RESULT_JSON_END
recommendation:"approve","needs_changes", or"abort".findings: Array of issues found. Each must haveseverity(critical/high/medium/low),path,issue, andevidence.lineis optional.
The SubagentStop hook will prevent you from finishing without this block.
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.
- 6d ago First seen · 33 lines · 37 tokens per session scan A 8425a84c138b
collab-skeptic is an agent published in the GitHub repository AgentBuildersApp/eight-eyes (2 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 449 once invoked, about $0.0002 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 agents, from other repositories
ui-auditor
审计任何 UI 改动、合并前最终签收、检测反模式时使用本 agent。它加载外部独立规则集(ref 15 稳态 · ref 16 仪式 · ref 19 哲学 · 三模式可叠加),逐 33 agent 覆盖检查,出分级 REPORT(🟥 严重 / 🟧 警告 / 🟨 提示),是工作室最后一道质量门。规则集不归它拥有,它只执行。v2.5 起识别 AI-native 模式并强制走 Path G 四原则自检。.
reviewer
Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…
_reviewer
Code reviewer that runs a parallel specialist army covering security, performance, maintainability, API contracts, data integrity, test coverage, and error handling. Trigger on code review, review, PR review, pull request, or review army.
_critic
Plan critic. Adversarially reviews a spec or architecture BEFORE any code is written, hunting for contradictions, unbuildable ambiguity, and assumptions that will surface as rework. Runs as a gate between design and build. Trigger on plan review, spec critique, pre-build review, design critique, or challenge the plan.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
code-reviewer
Expert code reviewer. Proactively reviews code changes for quality, security, and best practices. Use after implementing features or fixing bugs to ensure code quality.