compatibility-audit

A command that checks whether running agents meet the files, structure, and security requirements for working with Trinity, an agent-management system.

In plain words
What is it for?
Use it to inspect running agents for required configuration files, safe secret handling, and expected directories. It collects compatibility status, scores, issues, and recommendations.
Why use it?
It gathers consistent self-checks from multiple agents instead of checking each workspace manually.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/abilityai/trinity/compatibility-audit
Clone the repo
git clone --depth 1 https://github.com/Abilityai/trinity

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 633 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00633
Opus 5 $0.00000 $0.00316
Sonnet 5 $0.00000 $0.00127
Haiku 4.5 $0.00000 $0.00063

Measured 2d ago against content hash c2aca0d12b13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compatibility-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

config/agent-templates/trinity-system/.claude/commands/ops/compatibility-audit.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compatibility Audit

Audit all agents for Trinity compatibility by requesting self-diagnostics from each agent.

Instructions

  1. List all agents using mcp__trinity__list_agents

  2. Filter to running agents (skip stopped agents and trinity-system)

  3. For each running agent, call it using mcp__trinity__chat_with_agent with this prompt:

Run a Trinity compatibility self-diagnostic. Check your workspace for:

1. **Required Files**:
   - template.yaml (with name, display_name, description, resources)
   - CLAUDE.md (agent instructions)
   - .gitignore (excludes .mcp.json, .env, content/)

2. **Optional Files**:
   - .mcp.json.template (if using MCP servers)
   - .env.example (credential documentation)
   - dashboard.yaml (agent dashboard)

3. **Security**:
   - No secrets in committed files
   - .env and .mcp.json are gitignored

4. **Structure**:
   - content/ directory for large assets (if needed)
   - Proper .claude/ directory structure

Respond with a brief JSON report:
{
  "agent": "your-name",
  "compatible": true/false,
  "score": "X/10",
  "issues": ["issue1", "issue2"],
  "recommendations": ["rec1", "rec2"]
}
  1. Collect all responses and parse the JSON reports

  2. Generate consolidated report:

## Trinity Compatibility Audit Report
Generated: {timestamp}

### Summary
- Agents Audited: {count}
- Fully Compatible: {count}
- Issues Found: {count}
- Skipped (not running): {count}

### Compatibility Scores

| Agent | Score | Compatible | Issues |
|-------|-------|------------|--------|
| ... | X/10 | Yes/No | {count} |

### Issues by Agent

#### {agent-name}
- **Score**: X/10
- **Issues**:
  - {issue1}
  - {issue2}
- **Recommendations**:
  - {rec1}

### Common Issues
{List issues that appear across multiple agents}

### Recommendations
{Top priority fixes across the fleet}

Save Report

After generating the report:

  1. Create directory if needed: mkdir -p ~/reports/compliance
  2. Save with timestamp: ~/reports/compliance/YYYY-MM-DD_HHMM.md
  3. Confirm: "Report saved to ~/reports/compliance/YYYY-MM-DD_HHMM.md"

Read the full file on GitHub · 97 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 97 lines · 0 tokens per session scan A c2aca0d12b13

Subscribe to this mod's changes

compatibility-audit is a command published in the GitHub repository Abilityai/trinity (496 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 633 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.