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 skills/iris-eval/mcp-server/agent-evalnpx skills add iris-eval/mcp-server --skill agent-evalgit clone --depth 1 https://github.com/iris-eval/mcp-serverWhat 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 | $0.00096 | $0.00687 |
| Opus 5 | $0.00048 | $0.00344 |
| Sonnet 5 | $0.00019 | $0.00137 |
| Haiku 4.5 | $0.00010 | $0.00069 |
Grade A, and why
agent-eval 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Eval with Iris
Iris is an MCP server for agent evaluation. If this plugin is installed, its
nine tools are already available — no setup needed. If the tools are missing,
the server starts with npx -y @iris-eval/mcp-server in any MCP client config.
Core workflow (eval loop)
- Log the agent execution:
log_tracewith spans, tool calls, token usage, and cost. This builds the record everything else reads. - Score the output:
evaluate_outputruns 13 built-in rules across completeness, relevance, safety (19 PII patterns, 37 injection patterns, 25 hallucination markers), and cost. Heuristic, deterministic, free. Passinputso the hallucination signals can cross-check the output against the material the agent was given. - Judge semantically when heuristics aren't enough:
evaluate_with_llm_judge(templates: accuracy, helpfulness, safety, correctness, faithfulness). Requires the user's own API key inIRIS_ANTHROPIC_API_KEYorIRIS_OPENAI_API_KEY— Iris never proxies. - Verify citations in research/RAG outputs:
verify_citationsextracts citations, fetches sources (SSRF-guarded, opt-in), and checks each claim. - Inspect history:
get_traceswith filters; costs aggregate across agents and time windows.
Custom rules
deploy_rule registers a custom eval rule (Zod schema) that fires on every
matching evaluate_output. list_rules enumerates; delete_rule removes.
Use custom rules to encode product-specific quality bars — a required
disclaimer, banned phrases, output length bands, expected coverage terms.
Patterns worth suggesting
- Quality gate before ship: evaluate representative outputs; treat any safety-rule failure as blocking. Cost rules catch budget regressions.
- Eval-driven development: write rules first (the quality spec), then iterate the agent until they pass — the eval loop is the test suite.
- Regression tracking: log traces in CI runs; compare score drift across versions to catch silent quality decay (eval drift).
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 · 53 lines · 96 tokens per session scan A ebe212ba9261
agent-eval is a skill published in the GitHub repository iris-eval/mcp-server (7 stars, last pushed 8d ago), licensed MIT. It adds 96 tokens to every session and 687 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
agent-evaluation-reporting
Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.
ifixai
Guide the user through an independent iFixAi audit of their own agent, checking whether it does the job it is supposed to do given their business rules and org structure. Prefer pointing it at the user's REAL deployed agent over its HTTP endpoint (its actual tools, retrieval, and governance) with --provider http…
digital-health-clinical-asr-eval
Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipasource diagnostic). Not for ASR auth (/riva-asr).
comet
Comet — OpenSpec + Superpowers dual-star development workflow. Start with /comet for automatic phase detection and dispatch to subcommands. Five phases: open → design → build → verify → archive.
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session.
comet-hotfix
Comet 预设 —— 通过 open-build-verify-archive 短流程修复已有行为 bug。.