Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wyattowalsh/agentsnpx agentmods add rules/wyattowalsh/agents/opencode-agents-overlayWrote 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/rules/wyattowalsh/agents/opencode-agents-overlay)<a href="https://agentmods.dev/rules/wyattowalsh/agents/opencode-agents-overlay"><img src="https://agentmods.dev/badge/rules/wyattowalsh/agents/opencode-agents-overlay/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/wyattowalsh/agents/opencode-agents-overlay"><img src="https://agentmods.dev/badge/rules/wyattowalsh/agents/opencode-agents-overlay.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00669 | $0.00669 |
| Opus 5.5 | $0.00268 | $0.00268 |
| Sonnet 5.5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
opencode-agents-overlay 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 1mo 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCode Agent Runtime Overlay
This file documents OpenCode-specific runtime configuration for the agents defined in agents/*.md. It is loaded exclusively by the OpenCode harness as an instruction surface and is ignored by Codex, Claude Code, and Grok routes.
Machine-readable runtime overlays live in config/opencode-agents.json. Wagents sync merges that JSON with portable agents/*.md bodies into .opencode/agents/*.md (OpenCode-native frontmatter with permission objects, not portable tools: all).
Purpose
The portable agent contract (documented in AGENTS.md) defines a minimal, cross-platform schema. OpenCode extends this schema with runtime-specific keys for subagent behavior, UI theming, and granular permission rules. Those extensions are stored in config/opencode-agents.json to keep the canonical agent definitions portable.
Custom Keys (OpenCode-only)
| Field | Type | Description | Values |
|---|---|---|---|
mode |
string | Subagent execution mode | subagent |
temperature |
float | Sampling temperature for the agent | 0.1 (focused) or 0.2 (balanced) |
color |
string | UI color token in the OpenCode TUI | primary, secondary, etc. |
permission |
object | Nested permission rules for tool categories | edit, bash, webfetch, task |
Agent Runtime Configuration
Per-agent mode, temperature, color, and permission values are defined in config/opencode-agents.json. Generated OpenCode agent files are written to .opencode/agents/ by:
uv run python scripts/sync_agent_stack.py --apply --targets repo --platforms opencode
Or via just sync-opencode.
After apm compile -t opencode, always re-run that sync so APM's portable agent projection does not overwrite schema-valid OpenCode frontmatter.
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.
- 1mo ago First seen · 51 lines · 669 tokens per session scan A 13725c9e4db6
opencode-agents-overlay is a cursor rule published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 669 tokens to every session, about $0.0027 per session on Opus 5.5. 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.