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.
npx agentmods add commands/abilityai/trinity/service-checkgit clone --depth 1 https://github.com/Abilityai/trinityWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01010 |
| Opus 5 | $0.00000 | $0.00505 |
| Sonnet 5 | $0.00000 | $0.00202 |
| Haiku 4.5 | $0.00000 | $0.00101 |
Grade A, and why
service-check 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Service Check
Request each agent to run a self-diagnostic to validate their runtime setup.
IMPORTANT: This is a READ-ONLY service check. Agents must NOT modify any data in external systems. This is purely diagnostic validation.
Instructions
-
List all agents using
mcp__trinity__list_agents -
Filter to running agents (skip stopped agents and trinity-system)
-
For each running agent, call it using
mcp__trinity__chat_with_agentwith this prompt:
Run a SERVICE CHECK self-diagnostic. This is READ-ONLY - do NOT modify any external data.
Validate your runtime setup by checking:
1. **MCP Servers**: List configured servers from .mcp.json. For each server:
- Can you call a read-only/list operation? (e.g., list files, list items, get status)
- Report: working / failing / not configured
2. **Credentials**: Check .env file exists and has expected variables.
- Do NOT log credential values
- Report: present / missing / partially configured
3. **Workspace**: Verify key files exist:
- CLAUDE.md (your instructions)
- template.yaml (your config)
- Any domain-specific required files
4. **Tools**: Test that your core tools respond:
- File operations (read a test file)
- Any critical integrations
5. **Memory/State**: Check if persistent files are accessible:
- memory/ directory (if used)
- outputs/ directory (if used)
IMPORTANT CONSTRAINTS:
- DO NOT create, update, or delete any external resources
- DO NOT send messages, emails, or notifications
- DO NOT modify databases or APIs
- ONLY perform read/list/get operations
- If a tool only has write operations, skip it and note "write-only, skipped"
Respond with a brief JSON report:
{
"agent": "your-name",
"status": "healthy|degraded|unhealthy",
"checks": {
"mcp_servers": {"configured": 2, "working": 2, "failed": 0},
"credentials": "ok|missing|partial",
"workspace": "ok|issues",
"tools": "ok|some_failed|not_tested"
},
"issues": ["issue1", "issue2"],
"notes": ["any relevant observations"]
}
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.
- 2d ago First seen · 130 lines · 0 tokens per session scan A 8005f40a8b2e
service-check 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 1,010 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.