* Add doublecheck plugin: three-layer verification pipeline for AI output
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>
* Address review: fix tools YAML format, remove materialized artifacts
- 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>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- Make browser tester generic to support for chrome devotols mcp, playwright, agentic browser tools.
- Add Team lead and energetci peronsality to Orchestrator
- Add progress updates between phases/ waves
* feat: Prd/ steer support
- Add supprot for PRD
- Vscode steer/ queue support
- Consistent artifacts
- Improved parallel running; for researchers too
* chore: improve prd update support
* chore: Make reviewer use prd for compaince
* chore: imrpvoe websearch in researcher
* fix(gem-team): revert gem-team plugin version from 1.5.0 to 1.2.0
* Add Scientific Paper Research agent (BGPT MCP)
* Run npm run build to update README.agents.md
---------
Co-authored-by: connerlambden <connerlambden12@gmail.com>
* Modified tools to make the agent more efficient
* Added skill for importing Azure Infrastructure as Code
* Updated readme
* Some wording improvements
* Added / to skills path endings
* ran npm start
Add two new agents for the Vue.js ecosystem:
- nuxt-expert.agent.md: Expert Nuxt Developer agent covering Nuxt 3,
Nitro, rendering modes, data fetching, and legacy Nuxt 2 compatibility.
- vuejs-expert.agent.md: Expert Vue.js Frontend Engineer agent covering
Vue 3 Composition API, Pinia, Vue Router, TypeScript integration, and
legacy Vue 2/Options API compatibility.
Both agents use Claude Sonnet 4.5 and follow existing agent conventions.
README.agents.md regenerated via npm run build.
Updated agent guidelines to specify the use of accessibility_snapshot over visual screenshots for element identification. Accessibility snapshots provide structured DOM/ARIA data, which is more reliable for browser automation than pixel-based visual analysis.
Remove redundant `<operating_rules>`, agent-specific parameters, and
`<delegation_validation>` sections. This removes duplicate content
to ensure a single source of truth for the agent's behavior protocols
and configuration.
- Refined `gem-browser-tester` workflow to separate initialization from
execution and enforce an Observation-First loop.
- Added retry logic for transient failures (e.g., timeouts, network issues)
in browser automation tasks.
- Standardized artifact generation paths to `docs/plan/{plan_id}/`
across multiple agents.
- Updated failure actions to specify evidence capture locations
(logs, network) for improved debugging and traceability.
Introduce explicit sections for input, output, and verification criteria.
Define structured JSON output including detailed evidence paths and error counts.
Update workflow to reference new guides and move Observation-First loop to operating rules.
Clarify verification steps with specific pass/fail conditions for console, network, and accessibility checks.
- Remove redundant `<mission>` section from gem-browser-tester
- Add "Reflect" step to gem-documentation-writer for self-review on high-priority or failed tasks
- Refactor gem-orchestrator completion phase to generate a walkthrough markdown file instead of a review
- Update orchestrator rules to allow direct execution for creating walkthrough files
Remove "detailed thinking on" directive and consolidate operating_rules sections for consistency. Both gem-browser-tester.agent.md and gem-devops.agent.md now share standardized rules: unified tool activation phrasing ("Always activate tools before use"), merged context-efficient reading instructions, and removed agent-specific variations. This simplifies maintenance and ensures consistent behavior across different agent types while preserving core functionality like evidence storage, error handling, and output constraints.
Rename the Chrome-specific testing agent to a browser-agnostic version
to support multiple automation tools (Playwright, Chrome DevTools, etc.).
Updates all references in orchestrator and planner configurations, and
broadens the description and execution workflow to be tool-flexible.
Evidence storage rule clarified to apply primarily on failures.
