Source package available for inspection
The package could not be checked: plugin.json returned 403.
Static source inspection
doublecheck Agent Plugin
Apply a three-layer verification pipeline to AI output by extracting claims, finding supporting or contradicting sources, and flagging hallucination patterns for human review.
0 repository stars MIT Updated Aug 6, 2026
Reviewed seed
Doublecheck
with reviewed context.
The catalog adds a fixed-commit inventory, operating summary, prerequisites, and task-fit guidance for Doublecheck.
Installation
Install Doublecheck
Install from github/awesome-copilot in a compatible Agent Plugins client. Verified means a supporting source was found, not that a claim is definitively true. Search coverage and model judgment are limited, so experts remain responsible.
Terminal · Git sparse checkout
git clone --filter=blob:none --sparse https://github.com/github/awesome-copilot.git
cd awesome-copilot
git sparse-checkout set plugins/doublecheckVerified means a supporting source was found, not that a claim is definitively true. Search coverage and model judgment are limited, so experts remain responsible.
Review the fixed-source README and manifest before enabling the workflow.
Explainable standards check
Latest official standard could not be confirmed
Official latest version: 1.0.0 (Working Draft). The value is read from the official specification and cached for one day.
This is a static package-format check, not a security audit, quality score, malware scan, or guarantee of client compatibility.
Capabilities
What can you do with doublecheck?
Apply a three-layer verification pipeline to AI output by extracting claims, finding supporting or contradicting sources, and flagging hallucination patterns for human review.
The reviewed package declares 1 skill and 1 agent resource for its documented workflow.
- Extract verifiable claims and internal contradictions
- Search for supporting or contradicting sources
- Apply extra scrutiny to citations and statistics
- Run adversarial checks for hallucination patterns
- Rate claims as verified, plausible, unverified, disputed, or fabrication risk
- Produce linked reports for independent human review
Audit claims and sources
Extract verifiable claims and internal contradictions; Search for supporting or contradicting sources; Apply extra scrutiny to citations and statistics.
Flag uncertainty and fabrication risk
Run adversarial checks for hallucination patterns; Rate claims as verified, plausible, unverified, disputed, or fabrication risk; Produce linked reports for independent human review.
Practical workflow
A reviewed Doublecheck workflow
Pass 01 / Start
Audit claims and sources
Self-audit the target text, enumerate factual claims, and categorize them for verification.
Pass 02 / Verify
Flag uncertainty and fabrication risk
Search for evidence, run an adversarial review, assign confidence ratings, and return links for human judgment.
Package contents
What is included in doublecheck?
doublecheck declares 1 Skill, 0 MCP configurations, and 1 additional resource. The included-file links below point to the reviewed source repository.
Agent Skills
1
doublecheck
MCP servers
0
No runtime service
Package format
Agent Plugins
Official latest 1.0.0
Synced source content
Repository README
This README snapshot is stored by Agent Plugins Hub and refreshed by the daily GitHub synchronization pipeline. Remote images and embedded content are not loaded.
This repository does not currently provide a README snapshot. The plugin instructions below remain available.
Source documentation
Doublecheck source documentation
Rendered from the linked GitHub source. Raw HTML is disabled, scripts cannot execute, remote images are omitted, and external links open separately.
What this catalog entry adds
This entry summarizes the fixed reviewed manifest and README without extending the upstream package's claims.
Package scope
Apply a three-layer verification pipeline to AI output by extracting claims, finding supporting or contradicting sources, and flagging hallucination patterns for human review.
Declared package inventory
Skills: doublecheck
Agent resources: doublecheck
Agents are listed as resources because the extension declares them separately from skills. Only the real upstream plugin.json and README.md are listed as package files.
Documented capabilities
- Extract verifiable claims and internal contradictions
- Search for supporting or contradicting sources
- Apply extra scrutiny to citations and statistics
- Run adversarial checks for hallucination patterns
- Rate claims as verified, plausible, unverified, disputed, or fabrication risk
- Produce linked reports for independent human review
Workflow
- Self-audit the target text, enumerate factual claims, and categorize them for verification.
- Search for evidence, run an adversarial review, assign confidence ratings, and return links for human judgment.
Requirements and limitations
Verified means a supporting source was found, not that a claim is definitively true. Search coverage and model judgment are limited, so experts remain responsible.
Review generated output and consequential actions with the relevant maintainer or subject-matter expert.
License
The upstream manifest and README identify the plugin as MIT licensed.
Continue exploring
Related plugins
Developer Tools
Agent Plugins Example
The small official reference package for inspecting a portable manifest and migration workflow.
Developer Tools
acreadiness-cockpit
Drive Microsoft AgentRC from Copilot chat to assess AI readiness, generate flat or nested Copilot instructions, manage policies, and produce a self-contained HTML dashboard.
Developer Tools
awesome-copilot
Context-aware discovery of curated Copilot assets with three declared Skills, a project scaffold agent, and a Docker-based MCP server.