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 commands/matthewye/opencode-toolbox/autopilotgit clone --depth 1 https://github.com/MatthewYe/opencode-toolboxWhat 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 | $0.00066 | $0.08330 |
| Opus 5 | $0.00033 | $0.04165 |
| Sonnet 5 | $0.00013 | $0.01666 |
| Haiku 4.5 | $0.00007 | $0.00833 |
Grade A, and why
autopilot 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.
How it starts
The opening of the file, as written. The whole thing — 550 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute the autopilot orchestrator workflow below. Orchestrator MUST include explicit skill tool loading instructions in implementer and reviewer dispatch prompts — see "执行 implementer" and reviewer dispatch sections for the exact preamble format.
Issue 来源识别
autopilot 支持两种 issue 来源。根据 target 参数或扫描结果判断：
| target 特征 | 来源 | 状态机 | 合约文件 |
|---|---|---|---|
包含 / 的路径 |
本地 .scratch/ |
frontmatter Status: |
AGENT-BRIEF.md |
#N 或纯数字 N |
GitHub Issue | labels | issue body（含 AC） |
| 无参数扫描到本地 | 本地 .scratch/ |
frontmatter Status: |
AGENT-BRIEF.md |
| 无参数扫描到 GitHub | GitHub Issue | labels | issue body |
前置约定
本地 issue 模式
target使用绝对路径。如传入相对路径，拼接当前工作目录。issue.md以 YAML frontmatter 开头，Status字段在 frontmatter 中。- 更新 Status：用
edit工具修改 frontmatter 中的Status:行。 - 追加注释：在
## Comments节末尾加- <时间戳> autopilot: <内容>。无该节则在文件末尾创建。 - 合约文件：同目录下
AGENT-BRIEF.md。
GitHub Issue 模式
- 使用
ghCLI 操作 issue。从git remote -v自动推断 repo。 - 状态通过 labels 表达：
in-progress、resolved、needs-info。 - 追加注释用
gh issue comment <N> --body "..."。 - 合约来自 issue body（其中包含 Acceptance Criteria 和 What to build，由
to-issues创建）。 - 读取 issue：
gh issue view <N> --json number,title,body,labels,state。
共用概念
Status: ready-for-agent（本地 frontmatter）↔ labelready-for-agent（GitHub）Status: in-progress↔ labelin-progressStatus: resolved↔ labelresolvedStatus: needs-info↔ labelneeds-info
如果指定了 target
target 是路径（含 /）
- 确认
<target>/issue.md存在，不存在则报告错误并停止 - 确认
<target>/AGENT-BRIEF.md存在，不存在则报告错误并停止 - 读取
<target>/issue.md，检查Status:是否为ready-for-agent或in-progress - 非以上状态 → 回复当前状态并停止
- 更新 Status 为
in-progress - 设置
source = "local",id = <target> - 从
<target>推断 feature 目录（取 issue 目录的父级父级，如.scratch/auth/issues/01-login/→.scratch/auth/） - 设置
contract = <target>/AGENT-BRIEF.md的内容作为合约文本 - 跳到"交叉 Issue Suggestion 匹配"
target 是 GitHub issue 号（#N 或纯数字 N）
提取数字部分为 issueNumber：
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 · 550 lines · 66 tokens per session scan A 3b1df8854083
autopilot is a command published in the GitHub repository MatthewYe/opencode-toolbox (5 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 8,330 once invoked, about $0.0003 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.