challenge

Veracity challenger — adversarially challenges factual claims in high-stakes artifacts (security findings, research reports, design docs, gate decisions) with…

Skill by bpmforge

IndexedApache-2.0★ 2

Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/bpmforge-challenge

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Veracity challenger — adversarially challenges factual claims in high-stakes artifacts (security findings, research reports, design docs, gate decisions) with evidence-only verdicts: CONFIRMED / CONTRADICTED / UNVERIFIABLE. Every challenge cites file:line, URL, or validator output — no speculation. Auto-runs at HIGH/CRITICAL findings and Gate A/B; invoke manually to adversarially verify any output.

Use cases: design, security, research

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/challenge

What's inside

Skill name: challenge
Description: Veracity challenger — adversarially challenges factual claims in high-stakes artifacts (security findings, research reports, design docs, gate decisions) with evidence-only verdicts: CONFIRMED / CONTRADICTED / UNVERIFIABLE. Every challenge cites file:line, URL, or validator output — no speculation. Auto-runs at HIGH/CRITICAL findings and Gate A/B; invoke manually to adversarially verify any output.
License: Apache-2.0
Instructions: 13 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# Challenger

Load and follow the instructions in the `challenger` agent.

**Usage:**
- `/challenge` — Adversarially verify the claims in a target artifact; each claim gets CONFIRMED / CONTRADICTED / UNVERIFIABLE with cited evidence
- `/challenge --quick` — Produce the challenge list only, skipping the full rebuttal cycle (low-stakes passes)

**Protocol:** Full rules in `agents/shared/CHALLENGER_PROTOCOL.md` — including the Consensus & agreement map for concurrent multi-model runs (Act On / Consider / Noted / Dismissed; single-model runs remain fully valid). `sdlc-lead` calls the challenger automatically between Phase 2→3 and Phase 3→4; this skill is the manual entry point.

**Workflow:** Identify the checkable claims in the target artifact → gather evidence per claim (file:line, URL, validator/command output) → issue an evidence-only verdict per claim → list contradicted/unverifiable claims for remediation (no speculation, no new claims)

From bpmforge/attest, Apache-2.0.

Signals

Stars: 2
Forks: 1
Open issues: 0
Last commit (this folder): Aug 31, 2026 (1 month ago)
Last release: Oct 13, 2026 (16 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Apache-2.0
Repository: github.com/bpmforge/attest
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from bpmforge

Cite this page

challenge skill. Agent Mart. https://agentmart.dev/skills/bpmforge-challenge (last updated 2026-10-24)