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/whut09/opencode-plusplus/agents-mdgit clone --depth 1 https://github.com/whut09/opencode-plusplusWhat 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 | $0.01250 | $0.01250 |
| Opus 5 | $0.00625 | $0.00625 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
opencode-plusplus 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 yesterday.
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
Generated Agent Guide
L0 operating rules. Keep this file loaded by default; load deeper context only when the task requires it.
Must-Read Rules
- Inspect relevant source files before behavior-changing edits; generated summaries are not a source-of-truth replacement.
- Before finishing, run the relevant detected checks:
npm run build,npm run check,npm run lint,npm run format,npm run format:check,npm run prepublishOnly,npm run test. - Do not commit secrets, local config, dependency folders, or generated build output such as
opencode-plusplus.local.yml, API keys,node_modules/,dist/, or coverage artifacts. - Preserve existing project conventions and command patterns unless the source code clearly requires a change.
Default Workflow
- Read
AGENTS.mdonly before the task is concrete. - Agent-led handoff: run
opencode-plusplus run "<task>" .or inspect.agent-context/runs/<task-id>/; this writes context and boundaries but does not execute an agent. - Harness-led executor flow: run
opencode-plusplus orchestrate "<task>" . --executor mock|opencode|mimocode --executor-command "<command with {prompt}>" --max-loops 3 --checkpoint git-worktreewhen OpenCode++ should own multi-loop gates. - Do not load the full
.agent-context/directory unless L1/L2 context is insufficient. - Prefer source files over generated summaries for behavior, API, and test decisions.
Project Entrypoints
- Entrypoint:
src/cli/index.ts - Entrypoint:
src/mcp/server.ts - Anchor:
src/core/freshness.ts- 9 exports, 57 symbols - Anchor:
src/harness/control-plane/loop-controller.ts- 10 exports, 60 symbols - Anchor:
src/harness/control-plane/orchestrator.ts- 12 exports, 132 symbols
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.
- yesterday First seen · 82 lines · 1,250 tokens per session scan A a331cdc682da
opencode-plusplus AGENTS.md is an instructions file published in the GitHub repository whut09/opencode-plusplus (111 stars, last pushed 4d ago), licensed MIT. It adds 1,250 tokens to every session, about $0.0063 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 2026-08-30.
Other instructions, from other repositories
learn-harness-engineering CLAUDE.md
Instructions for walkinglabs/learn-harness-engineering, covering claude.md, project overview, commands, documentation site and run lecture code examples.
trueforge AGENTS.md
Instructions for truefoundry/trueforge, a project described as: The open-source agent harness - the runtime layer that turns an LLM into a working agent.
sprawling AGENTS.md
Instructions for 2youg1/sprawling, covering agents.md — how work is done in this repository, the loop, read before you write, one change, five steps and the rules a machine holds.
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.
duet-agent AGENTS.md
Instructions for dzhng/duet-agent, covering agent guidelines, treat types as documentation, keep names current, keep comments useful and prefer direct, local guarantees.
Gold-Band AGENTS.md
AGENTS.md instructions for diodeme/Gold-Band, covering 团队共享协作规则, 经验沉淀机制, 桌面端产品心智, 前端组件策略 and ui 交互详细规则.