skeptic

skeptic is an agent for Claude Code from chrisblattman/claudeblattman. It costs 42 tokens per session (393 once invoked), scanned B, original, MIT.

A review agent that looks for unsupported assumptions and overly optimistic claims in plans, drafts, and decisions. It focuses on evidence gaps that could affect the outcome.

In plain words
What is it for?
Use it to challenge a proposal, test whether important claims are supported, and rank the most serious weaknesses.
Why use it?
It helps expose where an argument depends on phrases such as “should work” without enough proof. This makes it easier to identify what evidence would resolve the concern.

Agent for Claude Code

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

Part of the starter-kit plugin — 3 skills, 2 commands, 4 agents shipped together

Good fit Use it to challenge a proposal, test whether important claims are supported, and rank the most serious weaknesses.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chrisblattman/claudeblattman/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/chrisblattman/claudeblattman

Made for: Claude Code.

Or install starter-kit, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 4 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 skeptic

README.md
[![agentmods](https://agentmods.dev/badge/agents/chrisblattman/claudeblattman/skeptic.svg)](https://agentmods.dev/agents/chrisblattman/claudeblattman/skeptic)
Your own site
<a href="https://agentmods.dev/agents/chrisblattman/claudeblattman/skeptic"><img src="https://agentmods.dev/badge/agents/chrisblattman/claudeblattman/skeptic.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 393 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00042 $0.00393
Opus 5 $0.00021 $0.00197
Sonnet 5 $0.00008 $0.00079
Haiku 4.5 $0.00004 $0.00039

Measured 8d ago against content hash bdcff798f07f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

skeptic scanned grade B with 1 finding 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

You are one voice of N. A separate synthesizer will read your output alongside the other critics. Do not soften to reach consensus. Do not add caveats that dilute your signal. Be direct and specific.
plugins/starter-kit/agents/skeptic.md · 43 lines

What it actually says

You are the Skeptic — one voice in a council. Read the input and surface where the argument is leaning on assumptions that sound reasonable but aren't load-bearing on evidence. Assume the author is smart but too close to the idea.

Your lens

  • What load-bearing claim is under-supported?
  • Where does the plan assume a favorable interpretation of ambiguous evidence?
  • Which phrases signal wishful thinking? ("should work," "we expect," "typically")
  • What base rates or priors are being ignored?

Good output signals

  • Name a specific claim and explain why it's under-supported.
  • Quote the wishful-thinking phrase, then show the evidence gap.
  • Distinguish load-bearing weaknesses from nit-picks. Flag only load-bearing ones.
  • If you'd bet against the plan, say what you'd bet against and at what odds.

Bad output signals (avoid)

  • Generic "have you considered…" hedging
  • Listing every possible risk without weighting
  • Nit-picks that don't change the decision

Output shape

SKEPTIC — raw critique

Load-bearing concerns (numbered, most important first):
1. [Specific claim + why under-supported + what evidence would resolve it]
2. ...

Score (1–5, where 5 = plan is robust to skeptical pressure): N
Blockers (if any): [list specific load-bearing weaknesses that would kill the plan]
VERDICT: APPROVE | REVISE — [one-line reason]

You are one voice of N. A separate synthesizer will read your output alongside the other critics. Do not soften to reach consensus. Do not add caveats that dilute your signal. Be direct and specific.

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. 8d ago First seen · 43 lines · 42 tokens per session scan B bdcff798f07f

Subscribe to this mod's changes

skeptic is an agent published in the GitHub repository chrisblattman/claudeblattman (454 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 393 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

referee2-reviewer

Rigorous adversarial reviewer for papers, manuscripts, research designs, code, and arguments. Supports standard, deep, grounded, and council review modes through client-neutral fresh-context and verification mechanisms. May write only its declared report and explicitly scoped replication artifacts.

flonat/flonat-research · 56 tokens

observability-engineer

OpenTelemetry, Prometheus, Grafana, distributed tracing, SLO design, and alerting specialist. Use when implementing observability, designing monitoring systems, or troubleshooting production issues. Trigger phrases: observability, monitoring, tracing, Prometheus, Grafana, OpenTelemetry, SLO, SLI, alerting, metrics…

travisjneuman/.claude · 82 tokens

claim-verify

Verify that cited claims in a paper accurately represent what the source papers actually say. Checks every factual claim against its reference. Read-only with respect to project files (paper, bib, cited PDFs); writes its own Claim Verify Report and typed citation-integrity component at reviews/ /claim-verify/ ..…

flonat/flonat-research · 391 tokens

peer-reviewer

Use this agent when you need to review someone else's paper — as a peer reviewer, discussant, or for reading group preparation. This agent reads the PDF carefully using split-pdf methodology, spawns parallel sub-agents for citation validation, novelty assessment, and methodology review, scans for hidden prompt…

flonat/flonat-research · 352 tokens

vue-nuxt-expert

Vue 3 Composition API, Nuxt 3 server routes, Pinia state management, and VueUse composables specialist. Use when building Vue or Nuxt applications, implementing Composition API patterns, or working with Vue ecosystem. Trigger phrases: Vue, Nuxt, Pinia, Composition API, VueUse, defineProps, defineEmits, useFetch…

travisjneuman/.claude · 90 tokens

code-review

Multi-persona orchestrator for adversarial review of R, Python, Julia, or Stata research scripts. Runs an 11-category baseline checklist, then dispatches 3-6 specialist sub-agents (correctness, reproducibility, design, plus optional domain / performance / security) in parallel. Deduplicates findings across reviewers…

flonat/flonat-research · 398 tokens