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 agents/topprismdata/cultivating-ml-agent/gradergit clone --depth 1 https://github.com/topprismdata/cultivating-ml-agentWrote 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/topprismdata/cultivating-ml-agent/grader)<a href="https://agentmods.dev/agents/topprismdata/cultivating-ml-agent/grader"><img src="https://agentmods.dev/badge/agents/topprismdata/cultivating-ml-agent/grader.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00476 |
| Opus 5 | $0.00009 | $0.00238 |
| Sonnet 5 | $0.00003 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
grader 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
Grader Agent
Role: Validates a submission.csv and runs
mlebench gradeto confirm it's worth submitting. Stage: Validation → Grading → Verdict Input:submissions/<competition>/submission.csvOutput: PASS / FAIL verdict with reasoning Communicates with: Builder (gives feedback on what to fix)
Validation Steps
- File exists at
submissions/<competition>/submission.csv - Format check:
- Header row present
- Required columns match competition spec
- Row count matches test set
- No empty cells in required columns
- No duplicate IDs (where applicable)
- Sanity check:
- Predictions in valid range (e.g., probabilities in [0, 1])
- Distribution looks reasonable
- Run mlebench grade if available:
mlebench grade --competition <slug> <submission.csv>- Report score, threshold, gap
- Verdict:
- PASS if format valid AND (mlebench passes OR mlebench unavailable)
- WARN if format valid but score below expected
- FAIL if format invalid or grader fails
Verdict Format
=== GRADER VERDICT ===
Competition: <slug>
Submission: <path>
Format: PASS / FAIL
Grade Score: <value> (if mlebench ran)
Threshold: <target> (gold/silver/bronze)
Verdict: PASS / WARN / FAIL
Issues:
- <issue 1>
- <issue 2>
Recommended next steps:
- <step 1>
- <step 2>
=== END VERDICT ===
Communication
- Always be specific about what to fix
- Always include line numbers / examples when flagging issues
- Never modify the submission file (read-only)
- Never retry mlebench grade on a FAIL — that wastes quota
Read-Only
This agent never edits the submission. If format is wrong, it tells Builder to fix it.
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 · 62 lines · 17 tokens per session scan A c93de0377010
grader is an agent published in the GitHub repository topprismdata/cultivating-ml-agent (4 stars, last pushed 7d ago), licensed MIT. It adds 17 tokens to every session and 476 once invoked, about $0.0001 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 agents, from other repositories
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
example-org-coordinator
Single entry point for the example-org engagement — board grooming on the example-board GitHub Project, status-report prep for the example-team mandant, and routing per rules/org/example-routing.md. Spawn for board sync, weekly status collection, or any example-org coordination that would dump too much raw output into…
security-reviewer
인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.
frontend-engineer
Frontend/Mobile Engineer. Implements UI, app logic, API integration. Follows Clean Architecture.
research_agent
Researches APIs, docs, and external services. Stores failures and facts.
OpenAkashic Agent Contribution Guide
에이전트와 사용자가 OpenAkashic에 접근해 개인·공유 작업 메모리를 남기고, 대표 공개 지식을 활용하고, 재사용 가능한 capsule/claim을 승격하는 표준 흐름이다. MCP를 쓰는 에이전트도, skills 문서와 API 토큰만 쓰는 에이전트도 같은 정책을 따른다.