Skip to content

Add doublecheck plugin: three-layer verification pipeline for AI output#978

Merged
aaronpowell merged 2 commits into
github:stagedfrom
dvelton:doublecheck
Mar 12, 2026
Merged

Add doublecheck plugin: three-layer verification pipeline for AI output#978
aaronpowell merged 2 commits into
github:stagedfrom
dvelton:doublecheck

Conversation

@dvelton
Copy link
Copy Markdown
Contributor

@dvelton dvelton commented Mar 12, 2026

What this adds

A new plugin called doublecheck that helps users verify AI-generated content before acting on it. Designed for sensitive contexts where mitigations for potential hallucinations are called for.

How it works

Three verification layers run in sequence:

  1. Self-Audit -- Extracts every verifiable claim from the target text. Categorizes them (factual, statistical, citation, entity, causal, temporal). Checks for internal contradictions.

  2. Source Verification -- Runs web searches for each claim. Produces clickable URLs so the user can verify independently. Gives extra scrutiny to citations, which are the highest-risk hallucination category.

  3. Adversarial Review -- Assumes the output contains errors and actively tries to find them. Checks against a hallucination pattern checklist: fabricated citations, unsourced statistics, confident specificity on uncertain topics, temporal confusion, overgeneralization, missing qualifiers.

Each claim gets a confidence rating: VERIFIED, PLAUSIBLE, UNVERIFIED, DISPUTED, or FABRICATION RISK.

Two modes

  • Persistent mode (use doublecheck): stays active for the conversation, auto-appends inline verification summaries to factual/analytical responses. Skips code and casual chat.
  • One-shot mode: run the full three-layer pipeline on specific text and get a detailed verification report.

Key design principle

The tool provides source links, not verdicts. "Here's where you can check" is trustworthy. "I checked and it's fine" is just more AI output. The human makes the final call.

What's included

File Type Description
skills/doublecheck/SKILL.md Skill Core verification pipeline with persistent and one-shot modes
skills/doublecheck/assets/verification-report-template.md Asset Structured report template
agents/doublecheck.agent.md Agent Interactive verification mode with follow-up capability
plugins/doublecheck/ Plugin Bundles the skill and agent as an installable package

Validation

  • npm run plugin:validate -- all plugins pass
  • npm run skill:validate -- all skills pass
  • npm run build -- README and marketplace.json updated
  • bash scripts/fix-line-endings.sh -- line endings normalized

Adds a new plugin that helps users verify AI-generated content before
acting on it. Designed for sensitive contexts (legal, medical, financial,
compliance) where hallucinations carry real consequences.

Three verification layers:
- Self-Audit: extracts verifiable claims, checks internal consistency
- Source Verification: web searches per claim, produces URLs for human review
- Adversarial Review: assumes errors exist, checks hallucination patterns

Supports persistent mode (auto-verifies every factual response inline)
and one-shot mode (full report on specific text). Confidence ratings:
VERIFIED, PLAUSIBLE, UNVERIFIED, DISPUTED, FABRICATION RISK.

Includes:
- Skill (skills/doublecheck/) with bundled report template
- Agent (agents/doublecheck.agent.md) for interactive verification
- Plugin package (plugins/doublecheck/) bundling both

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
@dvelton dvelton requested a review from aaronpowell as a code owner March 12, 2026 01:25
Copilot AI review requested due to automatic review settings March 12, 2026 01:25
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds a new doublecheck plugin/skill/agent intended to help users verify AI-generated content via a three-layer pipeline (self-audit → source verification → adversarial review), plus documentation/registry updates so it shows up in the repo’s listings and marketplace.

Changes:

  • Adds the doublecheck skill and a verification report template asset.
  • Adds a doublecheck agent and a doublecheck plugin definition (plugin.json + README) and registers it in marketplace/docs.
  • Updates docs index tables (README.skills.md, README.plugins.md, README.agents.md) and .github/plugin/marketplace.json.

Reviewed changes

Copilot reviewed 12 out of 12 changed files in this pull request and generated 3 comments.

Show a summary per file
File Description
skills/doublecheck/assets/verification-report-template.md Adds a structured markdown template for full verification reports.
skills/doublecheck/SKILL.md Defines the three-layer verification skill and persistent/one-shot behavior.
plugins/doublecheck/skills/doublecheck/assets/verification-report-template.md Copies the report template into the plugin package (currently committed).
plugins/doublecheck/skills/doublecheck/SKILL.md Copies the skill into the plugin package (currently committed).
plugins/doublecheck/agents/doublecheck.md Copies the agent into the plugin package (currently committed).
plugins/doublecheck/README.md Documents plugin purpose, layers, ratings, and usage patterns.
plugins/doublecheck/.github/plugin/plugin.json Declares the plugin metadata and references bundled agent/skill paths.
docs/README.skills.md Adds doublecheck to the skills index table.
docs/README.plugins.md Adds doublecheck to the plugins index table.
docs/README.agents.md Adds Doublecheck to the agents index table with install links.
agents/doublecheck.agent.md Adds the root agent definition for interactive verification.
.github/plugin/marketplace.json Registers the doublecheck plugin in the marketplace list.

You can also share your feedback on Copilot code review. Take the survey.

Comment thread agents/doublecheck.agent.md Outdated
Comment thread plugins/doublecheck/agents/doublecheck.md Outdated
Comment thread plugins/doublecheck/skills/doublecheck/SKILL.md Outdated
- Fix tools frontmatter in agents/doublecheck.agent.md to use standard
  YAML list format instead of flow sequence with trailing comma
- Remove plugins/doublecheck/agents/ and plugins/doublecheck/skills/
  from tracking; these paths are in .gitignore as CI-materialized
  artifacts that should not be committed

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
@aaronpowell aaronpowell merged commit eb7d223 into github:staged Mar 12, 2026
6 checks passed
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 9 out of 9 changed files in this pull request and generated 2 comments.


You can also share your feedback on Copilot code review. Take the survey.

Comment on lines +1 to +10
# Doublecheck

A three-layer verification pipeline for AI-generated output. Extracts verifiable claims, finds sources via web search, runs adversarial review for hallucination patterns, and produces a structured report with source links so humans can verify before acting.

## Why This Exists

AI hallucinations are a model-level problem. No plugin can fix them. But the *consequences* of hallucinations -- acting on fabricated citations, relying on made-up statistics, citing nonexistent case law -- can be mitigated by making verification fast and structured.

Doublecheck doesn't tell you what's true. It extracts every verifiable claim from AI output, searches for sources you can check independently, and flags anything that matches known hallucination patterns. You make the final call.

Copy link

Copilot AI Mar 12, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This plugin README is missing the standard sections that every other plugin README in this repo includes (notably Installation with the copilot plugin install ...@awesome-copilot command, plus Source and License). Without these, users have no canonical install instructions and the plugin README is inconsistent with the rest of plugins/*/README.md.

Copilot uses AI. Check for mistakes.
| Component | Type | Description |
|-----------|------|-------------|
| `doublecheck` | Skill | The core verification pipeline. Runs three layers and produces a structured report. |
| `Doublecheck` | Agent | Interactive verification mode for follow-up questions and deeper investigation. |
Copy link

Copilot AI Mar 12, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In the "What's Included" table, the agent is listed as Doublecheck, but throughout this repo plugin READMEs list agents by their identifier/filename (e.g., azure-principal-architect). Since the agent file is agents/doublecheck.agent.md (and the plugin spec path is ./agents/doublecheck.md), the identifier here should likely be doublecheck to avoid confusion about how to reference/install it.

Suggested change
| `Doublecheck` | Agent | Interactive verification mode for follow-up questions and deeper investigation. |
| `doublecheck` | Agent | Interactive verification mode for follow-up questions and deeper investigation. |

Copilot uses AI. Check for mistakes.
@aaronpowell
Copy link
Copy Markdown
Contributor

#codeowner

@github-actions
Copy link
Copy Markdown
Contributor

I've prepared the CODEOWNERS update for this PR, but encountered authentication limitations preventing automatic PR creation.

The following entries should be added to the CODEOWNERS file:

# Added via #codeowner from PR #978
/agents/doublecheck.agent.md `@dvelton`
/plugins/doublecheck/ `@dvelton`
/skills/doublecheck/ `@dvelton`

These entries assign @dvelton as the owner of the doublecheck agent, plugin, and skill directories contributed in this PR.

A maintainer with push access can create the CODEOWNERS update PR manually, or the workflow can be re-triggered with appropriate git credentials.

Generated by Codeowner Update Agent for issue #978

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants