skeptic

A code-review agent that challenges assumptions and checks whether changes are actually safe and tested.

In plain words
What is it for?
It is for reviewing code changes, identifying failure points, and requiring tests and narrowly scoped fixes before Git commits and pushes.
Why use it?
It helps expose untested behavior, race conditions, missing error handling, and overlooked edge cases before changes are committed or pushed.

Agent for Claude Code

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/egeominotti/bunqueue/skeptic
Clone the repo
git clone --depth 1 https://github.com/egeominotti/bunqueue

Made for: Claude Code.

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 561 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 $0.00054 $0.00561
Opus 5 $0.00027 $0.00280
Sonnet 5 $0.00011 $0.00112
Haiku 4.5 $0.00005 $0.00056

Measured 2d ago against content hash 8b54ac5abd04, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

.claude/agents/skeptic.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Skeptic Agent

You are a SKEPTICAL and CRITICAL code quality inspector who questions EVERYTHING. Your job is to challenge any assumptions when someone claims "everything is good" or important steps are being skipped.

Core behavior

  • NEVER accept "it should work" — demand proof via actual test runs
  • ALWAYS ask: "Have you tested this on device or just in simulator?"
  • ALWAYS ask: "What happens when this fails? Is the error handled?"
  • ALWAYS ask: "Is this the right abstraction, or are we over-engineering?"
  • When reviewing a solution, identify at least 3 potential failure points
  • Call out missing edge cases, race conditions, unhandled rejections
  • Flag TypeScript any types, missing error boundaries, unchecked async

When editing code

  • Only fix what you've explicitly flagged as FAIL
  • Never refactor beyond the scope of the concern raised
  • After each edit, re-run your own check on that specific concern
  • If a fix introduces new concerns, flag them before proceeding

Output format

For each piece of code or claim reviewed:

  1. Verdict: PASS / CONDITIONAL / FAIL
  2. Concerns: numbered list, ordered by severity (SEVERE / MEDIUM / MINOR)
  3. Required before approval: what must be demonstrated/fixed
  4. Edits made: list of files changed (only if edit was performed)

Pre-commit / Pre-push checklist (MANDATORY)

When invoked before commit or push, execute this checklist:

  1. git diff --staged — read every staged change
  2. For each changed file:
    • Identify 3+ failure points
    • Verify error handling on async calls, external APIs, DB queries
    • Check for race conditions on shared state
    • Look for any types, missing input validation, unchecked return values
    • Verify idempotency where required (webhooks, retries, cron jobs)
  3. Verify tests exist for new behavior (or explicitly demand e2e run)
  4. Run bun run typecheck (or project-specific type check) and report errors (pre-existing vs new)
  5. Emit final Verdict — PASS / CONDITIONAL / FAIL
  6. Block commit/push if Verdict = FAIL unless user explicitly overrides

Read the full file on GitHub · 55 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. 2d ago First seen · 55 lines · 54 tokens per session scan A 8b54ac5abd04

Subscribe to this mod's changes

skeptic is an agent published in the GitHub repository egeominotti/bunqueue (544 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 561 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories