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 instructions/yurymkomarov/opencode-agent-orchestration/agents-mdgit clone --depth 1 https://github.com/yurymkomarov/opencode-agent-orchestrationWhat 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 | $0.00331 | $0.00331 |
| Opus 5 | $0.00166 | $0.00166 |
| Sonnet 5 | $0.00066 | $0.00066 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
opencode-agent-orchestration AGENTS.md 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
Project Agent Instructions
Mission
This repository is managed through OpenCode with ai-cli-mcp workers:
- Codex/OpenAI is the default operator model for OpenCode.
- Claude is a mandatory deep-refactor and architecture reasoning worker.
- Google/Gemini compatibility is a mandatory long-context overview, documentation, and second-opinion worker.
- Codex CLI can also be used as an implementation, tests, bug fixing, and security-review worker.
Agent-specific worker profiles:
- Codex worker:
.agents/codex-worker.md - Claude worker:
.agents/claude-worker.md - Gemini worker:
.agents/gemini-worker.md
Safety Rules
- Do not access or modify files outside this repository.
- Do not read or print secrets.
- Do not modify
.env,.env.*, private keys, kubeconfigs, production credentials, or deployment secrets. - Do not run destructive commands unless explicitly requested.
- Do not run
kubectl,terraform apply,helm upgrade, or production deployment commands unless explicitly requested. - Prefer read-only analysis unless the user asks for implementation.
Work Style
- Before changing code, inspect the relevant files.
- For non-trivial changes, produce a short plan first.
- Prefer small, reviewable changes.
- Keep diffs focused.
- Do not mix refactoring and feature changes unless explicitly requested.
- Run relevant tests, linters, and type checks before claiming success.
- If tests cannot be run, explain exactly why.
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 · 39 lines · 331 tokens per session scan A c814f622d648
opencode-agent-orchestration AGENTS.md is an instructions file published in the GitHub repository yurymkomarov/opencode-agent-orchestration (2 stars, last pushed 2mo ago), licensed MIT. It adds 331 tokens to every session, about $0.0017 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 instructions, from other repositories
x-harness AGENTS.md
Instructions for BrianNguyen29/x-harness, covering x-harness agent contract, canonical tiers, completion rule, verifier rule and pgv rule.
helmor AGENTS.md
Instructions for dohooo/helmor, covering agents.md, what is helmor, commands, architecture and three-process model.
matt-skills-with-to-goal CLAUDE.md
Instructions for tt-a1i/matt-skills-with-to-goal: Skills are organized into bucket folders under skills/.
ephemeral-sandbox CLAUDE.md
Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.
pixir CLAUDE.md
Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.
codeTree CLAUDE.md
Instructions for ThinkyMiner/codeTree, covering claude.md, what this is, structural analysis tools (13), graph & onboarding tools (10) and supported languages.