Reality Checker Tram — Project Management agent for Claude Code
Tier-2 Harness Auditor for Team RAM.
How to install Reality Checker Tram
Installs to ~/.claude/agents/allura-ecosystem-allura-team-ram-reality-checker-tram.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Allura-Ecosystem/allura-team-ram/HEAD/.claude/agents/reality-checker-tram.md -o ~/.claude/agents/allura-ecosystem-allura-team-ram-reality-checker-tram.md Restart Claude Code, or start a new session, for it to be picked up.
What Reality Checker Tram does
name: reality-checker-tram description: "Tier-2 Harness Auditor for Team RAM. Cross-session, cross-project health audits. Verify invariants are enforced (kernel) not aspirational (prose); detect governance drift across copies; confirm lifecycle health (hooks firing, agents loading, curator promoting, DoD loop functional). Default verdict: NOT CERTIFIED until evidence flips it." model: sonnet color: "#B91C1C" tools: ["Read", "Grep", "Glob", "Bash", "allura-brain_memory_search", "allura-brain_
Alternatives in Project Management
- Statusline — Statusline feature specialist 538 ★
- Auto-detect From Project Manifest Files — Auto-detect from project manifest files agent 306 ★
- Autopsy — Full codebase health assessment — quantified health scores (0-100) per module across 6 dimensions 85 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Detect
Work out which framework a project is built on by reading its manifests and lockfiles, confirm it with the ope
Gan Contract Reviewer
GAN harness contract reviewer — audits a proposed sprint contract for specificity, comprehensiveness, scope, a
Ste Glossary Auditor
Audits a documentation set and the code for terminology drift, then proposes a project glossary and the matchi
Daedalai Lesson Scribe
Dispatch when a correction, gotcha, or non-obvious mistake has just been fixed in a DaedalAI-managed project a
Opensource Forker
Fork any project for open-sourcing. Copies files, strips secrets and credentials (20+ patterns), replaces inte
Ticket Light
Implements one ready-for-agent Ticket that copies a pattern already in the Project, with few acceptance criter
Related Skills
Code Auditor MCP
Architectural invariants and code quality analysis, enforced inside your AI agent's edit loop. MCP server + CL
Init Dev Kit
Install the agentic-dev-kit CLAUDE.md guardrails (root + apps/web) into the current project so the plugin's sk
Sanctuary Framework
Open-source security for AI agents: kernel-enforced egress control on macOS and Linux, keys only the operator