challenge

A review skill that challenges claims before they are reported as root causes, finished work, verified results, or irreversible actions. It requires fresh evidence from documentation, source code, or other real sources.

In plain words
What is it for?
Use it to challenge bug diagnoses, completion claims, verification results, deployments, commits, deletions, pushes, and other irreversible decisions.
Why use it?
It helps expose weak assumptions and untested failure cases before an owner relies on the conclusion. It is for reasoning and evidence, not for linting or type-checking code.

Skill for Claude CodeCodex

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 skills/fusengine/agents/challenge
Any agent
npx skills add fusengine/agents --skill challenge
Clone the repo
git clone --depth 1 https://github.com/fusengine/agents

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,546 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 $0.00052 $0.01546
Opus 5 $0.00026 $0.00773
Sonnet 5 $0.00010 $0.00309
Haiku 4.5 $0.00005 $0.00155

Measured yesterday against content hash 3a319df83e2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

challenge 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 yesterday.

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.

plugins/ai-pilot/skills/challenge/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

It fires systematically by claim TYPE, not by a stakes judgment: before a root-cause conclusion, a done/verified claim, an irreversible action (commit/deploy/rm/push), or a 2nd-time fix reaches the owner, whether inside an APEX task or in plain conversation -- plus automatically at every APEX eLicit round and Verify gate. It does not cover code correctness, lint, or type validation -- that stays sniper's lane at eXamine.

Challenge Skill

Reusable protocol behind the challenger agent. Also usable directly inside any expert agent's own eLicit step when a dedicated agent call is overkill -- the discipline is the same either way.

The 7 Principles

  1. Refute by default -- a claim is FALSE until proven otherwise. Never "are you sure?" -- always a concrete failure scenario + the untested hypothesis it exposes.
  2. Fresh context mandatory -- intake is the claim + its evidence ONLY, never the author's reasoning. Inheriting the author's angle reproduces the author's blind spot.
  3. Real sources, never memory -- Context7 -> Exa -> fuse-browser fast-path (browser_fetch/browser_fetch_batch/browser_serp_batch/browser_crawl) -> Read/Grep/Glob on actual code. Docs and code beat recollection.
  4. Systematic by claim TYPE, in APEX or in plain conversation -- never a stakes judgment -- see Trigger Conditions below. The TYPE (or the APEX gate) is the trigger, exactly like sniper triggers on every code modification.
  5. Bounded -- max 2 refutation rounds, then a mandatory verdict. No open-ended ping-pong.
  6. Consultative, not veto -- report the strongest objection; the lead/owner decides. Read-only, edits nothing.
  7. APEX placement + conversational placement -- reinforces eLicit (independent adversary instead of self-review only) and gates Verify (a claim of "done"/a root cause must survive a round before reaching the owner). Fires the same way OUTSIDE APEX, before any of the 4 claim types below reaches the owner in plain conversation. Does NOT touch eXamine -- that's sniper's code-correctness lane.

Read the full file on GitHub · 81 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. yesterday First seen · 81 lines · 52 tokens per session scan A 3a319df83e2c

Subscribe to this mod's changes

challenge is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed 28d ago), licensed MIT. It adds 52 tokens to every session and 1,546 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.