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.
git 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/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/agents/agentbuildersapp/eight-eyes/collab-skeptic"><img src="https://agentmods.dev/badge/agents/agentbuildersapp/eight-eyes/collab-skeptic.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 | $0.00037 | $0.00449 |
| Opus 5.5 | $0.00015 | $0.00180 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 2mo ago), licensed MIT. It adds 37 tokens to every session and 449 once invoked, about $0.0001 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 agents, from other repositories
ui-auditor
A user-interface audit agent that reviews UI changes and checks them against an external set of design and engineering rules. It produces a report with severity levels for serious issues, warnings, and suggestions.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
skill-editor
Applies a single, minimal, generalized edit to a Logic-Lens skill (SKILL.md / guide / shared file) given a concrete failure diagnosis. Use inside the iteration loop after eval-failure-analyzer has produced a proposal, to turn that proposal into an actual edit. Mutates files; does NOT run evals or sync the cache — it…
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…
ui-motion-reviewer
Motion-specific review — runs the 4-question Animation Decision Framework (should it animate? purpose? easing? duration?), catches ease-in on UI, transition:all, scale(0) entry, bounce/elastic defaults, animations on keyboard-triggered actions, prefers-reduced-motion gaps, and poorly-chosen spring vs duration…
ai-slop-cleaner
Clean AI-generated code anti-patterns — redundant comments, one-use abstractions, over-engineering, template slop — via behavior-preserving edits verified by compile/lint.