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/charles001-wong/autocode-flowWrote 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/commands/charles001-wong/autocode-flow/autocode)<a href="https://agentmods.dev/commands/charles001-wong/autocode-flow/autocode"><img src="https://agentmods.dev/badge/commands/charles001-wong/autocode-flow/autocode.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 | $0.00038 | $0.01833 |
| Opus 5 | $0.00019 | $0.00916 |
| Sonnet 5 | $0.00008 | $0.00367 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
autocode 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 6d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/autocode-flow:autocode — Autonomous Development Pipeline
Execute the full development pipeline automatically: Plan → TDD → Code → Test → Verify.
No human intervention required. Just describe what you want or point to a PRD file.
Input
$ARGUMENTS — One of:
- A feature description in natural language:
/autocode-flow:autocode 新增用户登录注册功能 - A PRD file reference:
/autocode-flow:autocode prd @docs/user-auth-prd.md - A GitHub issue URL:
/autocode-flow:autocode issue https://github.com/org/repo/issues/42
Orchestration Flow
Execute these phases sequentially and automatically. Do NOT stop to ask the user between phases. Each phase's output feeds directly into the next phase.
┌─────────────────────────────────────────────────────────────────────┐
│ /autocode-flow:autocode Pipeline │
│ │
│ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────────┐ │
│ │ PLAN │─►│ TDD │─►│ CODE │─►│ TEST │─►│ VERIFY │ │
│ │ │ │per step │ │per step│ │ full │ │lint+review │ │
│ └────────┘ └────────┘ └────────┘ └────────┘ └────────────┘ │
│ │
│ Optional (if enabled): │
│ ┌────────┐ ┌────────────┐ │
│ │ E2E │─►│ SUMMARY │ │
│ └────────┘ └────────────┘ │
└─────────────────────────────────────────────────────────────────────┘
Phase 1: PLAN (需求分析 & 任务拆解)
Goal: Convert the requirement into an ordered list of atomic implementation steps.
- If input is a PRD file, read and parse it.
- Search the codebase for related existing code, types, and patterns.
- Produce a structured plan:
{
"feature": "User login and registration",
"steps": [
{
"id": 1,
"title": "Create user model and database schema",
"files": ["internal/model/user.go", "internal/model/user_test.go"],
"test_spec": "TestUserModel_Validate: valid/invalid email, password length",
"depends_on": []
},
{
"id": 2,
"title": "Implement registration logic",
"files": ["internal/logic/register_logic.go", "internal/logic/register_logic_test.go"],
"test_spec": "TestRegisterLogic: success, duplicate email, weak password",
"depends_on": [1]
}
]
}
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.
- 6d ago First seen · 234 lines · 38 tokens per session scan A 2d9dca40686c
autocode is a command published in the GitHub repository charles001-wong/autocode-flow (2 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 1,833 once invoked, about $0.0002 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
kotlin-test
Enforce TDD workflow for Kotlin. Write Kotest tests first, then implement. Verify 80%+ coverage with Kover.
loop
Autonomous execution loop. Runs the TDD cycle repeatedly until all tasks in an epic are complete, with circuit breaker protection and PR workflow.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
cpp-test
Enforce TDD workflow for C++. Write GoogleTest tests first, then implement. Verify coverage with gcov/lcov.
go-test
Go TDD workflow with table-driven tests.
rust-test
Rust TDD workflow with unit and property tests.