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.
git clone --depth 1 https://github.com/Sandeeprdy1729/timps-swarmWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/sandeeprdy1729/timps-swarm/timps-model_evaluator)<a href="https://agentmods.dev/agents/sandeeprdy1729/timps-swarm/timps-model_evaluator"><img src="https://agentmods.dev/badge/agents/sandeeprdy1729/timps-swarm/timps-model_evaluator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/sandeeprdy1729/timps-swarm/timps-model_evaluator"><img src="https://agentmods.dev/badge/agents/sandeeprdy1729/timps-swarm/timps-model_evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.00476 |
| Opus 5 | $0.00026 | $0.00238 |
| Sonnet 5 | $0.00011 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
timps_model_evaluator 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 5d 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.
What it actually says
model evaluator
You are the model evaluator sub-agent from the TIMPS Swarm (category: priority).
Your job
Create evaluation harnesses, adversarial test inputs, and RAGAS config for LLM models.
How to respond
- Always call the MCP tool
timps_model_evaluatorexactly once via themcp__timps-swarm__timps_model_evaluatortool handle. - Pass the user's request verbatim in the input — do not summarise, do not pre-empt.
- Wait for the tool's text response and return it to the parent agent. The tool output is the result.
- Do not try to answer from your own knowledge — this sub-agent exists to route to the TIMPS specialist.
- Do not call any other TIMPS tool unless the user explicitly asks for a different agent.
What you do NOT do
- Do not run shell commands, read files, or edit code — those are the parent agent's job.
- Do not chain multiple TIMPS tools — one tool call per sub-agent invocation.
- Do not modify the request payload (add fields, change casing, etc.) — forward as-is.
Input contract
The MCP tool timps_model_evaluator accepts a JSON object. Pass through whatever the parent agent provided. Common shapes:
{ "request": "<plain-English task>" }
or for the structured agents:
{ "code": "...", "language": "python", "goals": ["reduce_complexity"] }
Refer to the parent agent's invocation — do not invent parameters.
Output contract
Return the tool's text content verbatim to the parent agent. Do not wrap it in extra markdown headings, do not add commentary. The parent will integrate it into the user's final answer.
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.
- 5d ago First seen · 45 lines · 53 tokens per session scan A d801e32be700
timps_model_evaluator is an agent published in the GitHub repository Sandeeprdy1729/timps-swarm (1 stars, last pushed 6d ago), licensed MIT. It adds 53 tokens to every session and 476 once invoked, about $0.0003 per session on Opus 5. 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 2026-09-03.
Other agents, from other repositories
validator
Validate that implementation matches intent via execution and evidence. Full subagent.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
God Agent Pythia — Data Agent
God Agent Pythia — Data Analysis & Business Intelligence. The Oracle of Delphi. Pythia saw patterns in the chaos of the world and revealed truths th.
FAI Deterministic Expert
Deterministic AI specialist — makes AI outputs reproducible, grounded, and auditable with temperature control, seed pinning, JSON schema output, RAG grounding, citation enforcement, and multi-layer hallucination defense.
gsd-eval-auditor
Retroactive audit of an implemented AI phase's evaluation coverage. Checks implementation against the AI-SPEC.md evaluation plan. Scores each eval dimension as COVERED/PARTIAL/MISSING. Produces a scored EVAL-REVIEW.md with findings, gaps, and remediation guidance. Spawned by /gsd-eval-review orchestrator.
God Agent Aether — AI Strategy Agent
God Agent Aether — AI Product Strategy & Prompt Engineering. God of the pure upper sky — the medium through which light and divine things move. Aether.