collab-skeptic

collab-skeptic is an agent for Claude Code from AgentBuildersApp/eight-eyes. It costs 37 tokens per session (449 once invoked), scanned A, original, MIT.

A read-only reviewer for the review phase of a collaborative coding task. It independently examines the repository changes and acceptance criteria without seeing the implementer's explanation.

In plain words
What is it for?
It helps review changed files, check requirements, identify hidden dependencies, and recommend whether the work should be approved.
Why use it?
It provides a second perspective that can reveal missed requirements, edge cases, regressions, and rollback risks.

Agent for Claude Code

Written for Claude Code: SubagentStop hook event.

Part of the 8eyes plugin — 2 skills, 2 commands, 8 agents, 7 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/agentbuildersapp/eight-eyes/collab-skeptic
Clone the repo
git clone --depth 1 https://github.com/AgentBuildersApp/eight-eyes

Made for: Claude Code.

Or install 8eyes, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 8 agents, 7 hooks.

Wrote 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.

agentmods badge for collab-skeptic

README.md
[![agentmods](https://agentmods.dev/badge/agents/agentbuildersapp/eight-eyes/collab-skeptic.svg)](https://agentmods.dev/agents/agentbuildersapp/eight-eyes/collab-skeptic)
Your own site
<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>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash 8425a84c138b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

adapters/copilot_cli/agents/collab-skeptic.agent.md · 33 lines

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

  1. 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.
  2. Inspect the changed files, repository state, and acceptance criteria directly.
  3. Prioritize: requirement misses, edge cases, regression risk, rollback risk, hidden coupling, and local-success/global-failure patterns.
  4. You are read-only. Never try to mutate files.
  5. 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 have severity (critical/high/medium/low), path, issue, and evidence. line is optional.

The SubagentStop hook will prevent you from finishing without this block.

Changes

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.

  1. 6d ago First seen · 33 lines · 37 tokens per session scan A 8425a84c138b

Subscribe to this mod's changes

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.

Related

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。.

SuanFishXYY/suanfish-design-system · 139 tokens

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…

qwerfunch/cladding · 68 tokens

_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.

navox-labs/agents · 49 tokens

_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.

navox-labs/agents · 68 tokens

consistency-and-history

Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.

ncoevoet/claude-review-all · 34 tokens

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.

yu-iskw/coding-agent-fabric · 34 tokens