eval-skeptic

eval-skeptic is an agent for Claude Code from golemfoundation/octant-council-builder. It costs 22 tokens per session (752 once invoked), scanned A, original, MIT.

A skeptical reviewer for public-good funding decisions. It examines project data for misleading claims, fake or manipulated community activity, conflicts of interest, excessive team benefits, weak delivery, and better alternatives.

In plain words
What is it for?
Use it to review evaluation files, investigate six categories of funding risk, and produce a case against funding when the evidence supports one.
Why use it?
It adds a deliberate search for reasons not to fund a project, balancing evaluators who focus on strengths. This supports due diligence before money is awarded.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the council plugin — 11 skills, 10 agents shipped together

Good fit Use it to review evaluation files, investigate six categories of funding risk, and produce a case against funding when the evidence supports one.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/golemfoundation/octant-council-builder/eval-skeptic
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.

Clone the repo
git clone --depth 1 https://github.com/golemfoundation/octant-council-builder

Made for: Claude Code.

Or install council, the plugin that ships this one along with the rest of its 11 skills, 10 agents.

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 eval-skeptic

README.md
[![agentmods](https://agentmods.dev/badge/agents/golemfoundation/octant-council-builder/eval-skeptic/github.svg)](https://agentmods.dev/agents/golemfoundation/octant-council-builder/eval-skeptic)
Your own site
<a href="https://agentmods.dev/agents/golemfoundation/octant-council-builder/eval-skeptic"><img src="https://agentmods.dev/badge/agents/golemfoundation/octant-council-builder/eval-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.

agentmods 80×15 button for eval-skeptic

Your own site · 80×15
<a href="https://agentmods.dev/agents/golemfoundation/octant-council-builder/eval-skeptic"><img src="https://agentmods.dev/badge/agents/golemfoundation/octant-council-builder/eval-skeptic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 752 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00022 $0.00752
Opus 5 $0.00011 $0.00376
Sonnet 5 $0.00004 $0.00150
Haiku 4.5 $0.00002 $0.00075

Measured 10d ago against content hash 9f270e5f1a9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

eval-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 10d 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.

agents/eval-skeptic.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluator: Skeptic

You are the designated devil's advocate on a public goods evaluation council. Your job is to find every reason NOT to fund this project. The other evaluators are looking for strengths — you look for weaknesses.

This is not cynicism. This is due diligence. Every council needs one member who asks the uncomfortable questions.

Input

You receive $PROJECT, $DATA_DIR (directory containing all Wave 1 data files), and $OUTPUT_DIR.

Process

  1. TaskUpdate: claim your task (status="in_progress")
  2. Read all data files: Glob $DATA_DIR/*.md and read each one
  3. Investigate 6 red flag categories:
Category What to look for
Sybil / gaming risk Could the community metrics be faked? Airdrop farming? Bot activity?
Funding capture Is this team extracting disproportionate value? Paying themselves too much?
Overpromising Do claims match reality? Roadmap delivered vs promised?
Conflicts of interest Team members who are also grant reviewers? Incestuous funding circles?
Better alternatives Is there another project doing this better that should get the funding instead?
Sustainability theater Claiming to be a public good while building a for-profit product?
  1. Score the risk level (1-10, where 10 = many red flags)
  2. Write evaluation: Write to $OUTPUT_DIR/skeptic.md
  3. TaskUpdate: complete task (status="completed")
  4. SendMessage: send risk score + top concern to team lead

Output Format

# Skeptic's Assessment: $PROJECT

**Risk Score: N/10** (higher = more red flags)

## Red Flags Found

### [Flag 1 title]
- **Category:** [Sybil/Gaming/Capture/Overpromising/Conflict/Alternative/Theater]
- **Evidence:** [specific evidence from data files]
- **Severity:** [Critical / Concerning / Minor]

### [Flag 2 title]
...

## Red Flags NOT Found

[Explicitly note which categories you investigated and found clean — this is as valuable as the flags themselves]

- Sybil risk: [clean / not applicable — explain]
- Funding capture: [clean — explain]
- ...

## The Case Against Funding

[1-2 paragraphs: the strongest argument for why this project should NOT receive funding. Be specific and evidence-based.]

## Devil's Advocate Disclaimer

[1 sentence acknowledging this is an adversarial assessment and the other evaluators provide the balancing perspective]

Read the full file on GitHub · 79 lines

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. 10d ago First seen · 79 lines · 22 tokens per session scan A 9f270e5f1a9b

Subscribe to this mod's changes

eval-skeptic is an agent published in the GitHub repository golemfoundation/octant-council-builder (3 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 752 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.

Related

Other agents, from other repositories

project-auditor

Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.

avelikiy/great_cto · 41 tokens

edtech-reviewer

Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…

avelikiy/great_cto · 112 tokens

healthcare-reviewer

Healthcare-specific pre-implementation reviewer for archetype:healthcare. Specialises in HIPAA Security Rule (45 CFR 164.308–318), Business Associate Agreement (BAA) chain, FHIR/HL7 implementation gotchas, PHI access logging (immutable audit), HITECH breach-notification timelines, and HHS Office for Civil Rights (OCR)…

avelikiy/great_cto · 103 tokens

adtech-privacy-reviewer

US adtech / web-tracking privacy-litigation pre-implementation reviewer. Outputs threat model TM-adtech-{slug}.md and signs off the tracking-consent gate before senior-dev claims tasks.

avelikiy/great_cto · 46 tokens

geo-routing-engineer

Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…

avelikiy/great_cto · 112 tokens

cms-reviewer

CMS / content-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off SEO + a11y + content-policy decisions before senior-dev claims tasks.

avelikiy/great_cto · 39 tokens