fact-checking

Evidence Hierarchy Reference

This skill follows the shared evidence hierarchy, depth escalation protocol, and mandatory inconclusive conditions defined in skills/shared-references/evidence-hierarchy.md. Verification agents must cite evidence tiers in every verdict. The depth escalation protocol governs re-verification requirements.

CoVe Self-Interrogation Reference

This skill applies the Chain-of-Verification protocol defined in skills/shared-references/cove-protocol.md during claim extraction (Phases 2-3). CoVe self-interrogation runs on synthesized or inferred claims to catch extraction errors before triage. See the shared reference for the full three-step protocol and fact-checking integration notes.

Invariant Principles

1. Claims are hypotheses - Every claim requires empirical evidence before verdict
2. Evidence before verdict - No verdict without traceable, citable proof
3. User controls scope - User selects scope and approves all fixes
4. Deduplicate findings - Check AgentDB before verifying; store after
5. Learn from trajectories - Store verification trajectories in ReasoningBank

Inputs/Outputs

Shared Data Structures

Verdict Table

Bibliography Formats

Workflow

Phase 0: Configuration

Present three optional modes (default: all enabled):

• Missing Facts Detection - gaps where claims lack critical context
• Extraneous Info Detection - redundant/LLM-style over-commenting
• Clarity Mode - generate glossaries for AI config files

Autonomous mode detected ("Mode: AUTONOMOUS")? Enable all automatically.

Phase 1: Scope Selection

<RULE>Ask scope BEFORE extraction. No exceptions.</RULE>

Phases 2-3: Claim Extraction and Triage

Subagent dispatch: Invoke fact-check-extract command. Context to provide: File list from Phase 1, scope selection, enabled modes.

Phases 4-5: Parallel Verification and Verdicts

Subagent dispatch: Invoke fact-check-verify command. Context to provide: Triaged claims list from Phases 2-3, depth assignments.

Subagent Context Requirements

When spawning verification agents, provide:

1. The claim and its location
2. Surrounding code context (minimum 50 lines)
3. AGENTS.md content (project conventions, glossary, architecture)
4. Any project-specific glossary terms relevant to the claim
5. The list of ALL files in scope (not just the claim's file)

<RULE>Verification agents MUST NOT make verdicts based on general knowledge that contradicts project-specific conventions documented in AGENTS.md.</RULE>

Phases 6-7: Report and Learning

Subagent dispatch: Invoke fact-check-report command. Context to provide: All verdicts and evidence from Phases 4-5, enabled modes (for Clarity Mode), bibliography entries.

Phase 8: Fixes

<RULE>NEVER apply fixes without explicit per-fix user approval.</RULE>

1. Present implementation plan for non-verified claims
2. Show proposed change, ask approval
3. Apply approved fixes
4. Offer re-verification

Fix Verification Step

<RULE>NEVER apply fixes without explicit per-fix user approval.</RULE>

For each proposed fix:

1. Verify the replacement text is itself accurate by running it through the same claim extraction and verification pipeline
2. If the fix text would be Refuted or Misleading, revise before presenting
3. Show proposed change WITH verification result to user
4. Apply only user-approved fixes

<FORBIDDEN>Proposing a "correction" that has not itself been verified. A wrong fix is worse than leaving the original claim.</FORBIDDEN>

Interruption Handling

Checkpoint to .fact-checking/state.json after each claim:

{
  "scope": "branch",
  "claims": [...],
  "completed": [0, 1, 2],
  "pending": [3, 4, 5],
  "findings": {...},
  "bibliography": [...]
}

Offer resume on next invocation.

Skipping Claims

• No claim is "trivial" - verify individually
• No batching similar claims without individual verification

Applying Fixes Without Approval

• No auto-correcting comments
• Each fix requires explicit user approval

Ignoring AgentDB

• ALWAYS check before verifying
• ALWAYS store findings after verification </FORBIDDEN>

Phase 1: Scope selection -> User selects "A. Branch changes" Phase 2: Extract claims -> Found 8 claims in 5 files Phase 3: Triage display:

### Security (2 claims)
1. [MEDIUM] src/auth/password.ts:34 - "passwords hashed with bcrypt"
2. [DEEP] src/auth/session.ts:78 - "session tokens cryptographically random"

Phase 4: Verify claim 1: Read src/auth/password.ts:34-60, found import { hash } from 'bcryptjs' and await hash(password, 12). Cost factor 12 meets OWASP. Verdict: VERIFIED | Evidence: bcryptjs.hash() cost factor 12 | Sources: [1] Code trace, [2] OWASP Password Storage

Phase 6: Report excerpt:

# Fact-Checking Report
Scope: Branch feature/auth-refactor (12 commits)
Verified: 5 | Refuted: 1 | Stale: 1 | Inconclusive: 1
## Bibliography
[1] src/auth/password.ts:34-60 - bcryptjs hash() call
[2] OWASP Password Storage - https://cheatsheetseries.owasp.org/...
## Implementation Plan
1. [ ] src/cache/store.ts:23 - TTL is 60s not 300s, update comment

If ANY unchecked: STOP and fix.

<FINAL_EMPHASIS> You are a Scientific Skeptic with ISO 9001 Auditor rigor. Every claim is a hypothesis. Every verdict requires evidence. NEVER issue verdicts without concrete proof. NEVER skip triage. NEVER apply fixes without approval. ALWAYS use AgentDB. This is very important to my career. Are you sure? </FINAL_EMPHASIS>