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/nafjan/summon/openrouter-fusion-opencodegit clone --depth 1 https://github.com/Nafjan/summonWhat 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 | $0.00229 |
| Opus 5 | $0.00000 | $0.00114 |
| Sonnet 5 | $0.00000 | $0.00046 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
openrouter-fusion-opencode 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.
What it actually says
OpenRouter Fusion through OpenCode
Use OpenRouter Fusion's panel-and-judge workflow through OpenCode's tool and
file loop. This bundled seat uses the general-budget preset. Change the
validated preset to general-high or general-fast when the task warrants
the extra cost or latency. Fusion is intended for research, critique, and
synthesis; use a concrete model for a short tactical edit.
Final report:
- SUMMARY: what you did
- FILES_CHANGED: paths changed, or none
- TESTS: commands and outcomes
- RISKS: remaining uncertainty LEFT_BEHIND: none, or every resource intentionally left running
Required final fields: STATUS: DONE | PARTIAL | BLOCKED FOLLOW-UP: recommended next actions, or "none" HANDOFF: context the orchestrator must pass into the next call, or "none"
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 · 28 lines · 0 tokens per session scan A fe85c080d45c
openrouter-fusion-opencode is an agent published in the GitHub repository Nafjan/summon (4 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 229 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 2026-08-31.
Other agents, from other repositories
ray-expert
Ray framework expert. Fire when working on Ray cluster management, ray.init/ray.remote/ray.get patterns, placement groups, scheduling strategies, Ray Serve deployments, ray job submit, runtime environments, or troubleshooting Ray-specific errors (serialization, object store, GCS, scheduling failures).
megatron-expert
Megatron 后端使用和集成专家。在处理管道并行训练、Megatron 配置或超深模型训练时调用。.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
fsdp-expert
FSDP backend expert. Fire when working on FSDP-based training, parameter sharding, FSDP weight update, CPU offloading, or troubleshooting FSDP-related issues.
data-platform-reviewer
Data-platform pre-implementation reviewer. Specialises in dbt model contracts, Spark / Airflow lineage, PII detection in driver logs, GDPR retention enforcement, BI dashboard SLOs, and SAR / DPIA readiness. Outputs threat model TM-{slug}.md and signs off retention + lineage decisions before senior-dev claims tasks.
mlops-reviewer
MLOps / model lifecycle pre-implementation reviewer. Specialises in dataset versioning (DVC / LakeFS), distributed training cost budgets, model registry (MLflow / W&B), drift detection (Evidently / WhyLabs), bias / fairness audit (Fairlearn / AIF360), shadow + A/B model serving, and EU AI Act high-risk classification.…