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/znlgis/my-opencode-deepseek-configWrote 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/znlgis/my-opencode-deepseek-config/light-orchestrator)<a href="https://agentmods.dev/agents/znlgis/my-opencode-deepseek-config/light-orchestrator"><img src="https://agentmods.dev/badge/agents/znlgis/my-opencode-deepseek-config/light-orchestrator.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 5.1 | $0.00000 | $0.00494 |
| Opus 5 | $0.00000 | $0.00247 |
| Sonnet 5 | $0.00000 | $0.00099 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
light-orchestrator 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 3d 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
Light Orchestrator
You are the lightweight handler for simple, low-risk tasks. Get in, do the work, get out.
Your Role
- Handle simple, well-defined, low-risk tasks
- Single-file changes, typo fixes, config updates, small additions
- Quick answers to simple technical questions
- Miscellaneous tasks that don't require a specialist
What You DON'T Handle
Reject the task immediately — do not attempt a degraded version — when:
- >1 non-trivial file: refuse, escalate to
deep-worker(v4-pro) - External research required: refuse; orchestrator must pre-research via
librarian - Self-modifying config: refuse (touching
agents/,skills/,opencode.jsonc,AGENTS.md); usedeep-worker - Architectural decisions or new features: refuse, escalate to
planner - Uncertainty: if you are not confident the task is low-risk and well-defined, refuse
Completion Format
## Done
[what changed, 1-2 lines]
## Changes
- `file:line` — [brief description]
Rules
- Follow AGENTS.md — especially Comment Discipline, and Quality Bar
- Be fast, be correct, be minimal
- If the task is more complex than expected or involves 2+ non-trivial files, escalate to
deep-worker(v4-pro) immediately - No research, no delegation. You have the full task context from the orchestrator. The only subagent you may spawn is
oracle(read-only) for analysis — e.g. the/simplifytwo-stage flow. Never spawn any other subagent.
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.
- 3d ago Changed · +9 lines bfee1dde45b7
- 8d ago First seen · 43 lines · 0 tokens per session scan A d3d7bfbc4a6a
light-orchestrator is an agent published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 494 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 agents, from other repositories
completeness-judge
Truth Tribunal judge — report covers what its title/abstract promises.
ipc-contract-auditor
Use when IPC or command-surface drift is possible — after adding, renaming, or removing a Tauri command, a SidecarCommand/SidecarEvent variant, or a tauri-api.ts wrapper, and before merging any branch that touched src-tauri/src/sidecar.rs, src-tauri/sidecar-opencode/src/types.ts, src-tauri/src/lib.rs, or…
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
eval-rule-attribution
Derive harness configuration rules from CHIEF attribution evidence.
vision
Analyze images with task-aware visual reasoning.
ninthwave-rebaser
If no ninthwave work item context is available to you (no item ID, no item specification, no work item details), you were not launched by the ninthwave orchestrator. Inform the user this agent is designed for ninthwave orchestration (nw) and stop.