ABCoder: Recheck

A command that critically checks whether a requested coding task can be implemented in a repository. It uses mcpabcoder to inspect the repository structure and relevant code nodes in detail.

In plain words
What is it for?
Use it to inspect repositories, packages, files, and specific code structures, then assess feasibility, identify risks, and suggest changes needed to carry out a CODE_TASK.
Why use it?
It exposes technical risks, missing support, and unnecessary changes before implementation starts. The analysis also checks whether existing functionality can be reused.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/cloudwego/abcoder/recheck
Clone the repo
git clone --depth 1 https://github.com/cloudwego/abcoder

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 432 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.00432
Opus 5 $0.00010 $0.00216
Sonnet 5 $0.00004 $0.00086
Haiku 4.5 $0.00002 $0.00043

Measured yesterday against content hash 0cd1407d48e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ABCoder: Recheck 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.

internal/cmd/assets/.claude/commands/abcoder/recheck.md · 33 lines

What it actually says

从原始需求出发,使用 mcp__abcoder 进行批判性分析,以验证 CODE_TASK 的技术可行性。

Guardrails

  • 批判性思考,保持诚实:确保方案可实现需求、无技术风险、最大化复用已有功能、最小化改动。
  • 严格使用 mcp__abcoder 验证技术细节,禁止假设。
  • 下钻到 mcp__abcoder__get_ast_node 粒度进行验证。

Steps Track these steps as TODOs and complete them one by one.

  1. mcp__abcoder__get_repo_structure 开始,获取目标仓库结构。
  2. 定位相关的 package 和 node。
  3. 使用 mcp__abcoder__get_ast_node 深入分析相关代码节点,验证方案的可行性。
  4. 检查方案是否可以实现 CODE_TASK 中的所有需求。
  5. 识别并报告任何潜在的技术风险。
  6. 验证是否最大化复用了已有功能,是否最小化了改动。
  7. 如发现问题,提出具体的修改建议或后续问题。
  8. 总结分析结果,明确指出方案是否可以执行。

Reference

  • mcp__abcoder__list_repos - 列出所有可用仓库
  • mcp__abcoder__get_repo_structure - 获取仓库结构(必须作为第一步)
  • mcp__abcoder__get_package_structure - 获取 package 结构
  • mcp__abcoder__get_file_structure - 获取文件结构
  • mcp__abcoder__get_ast_node - 获取 AST 节点详情(下钻验证)
Changes

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.

  1. yesterday First seen · 33 lines · 0 tokens per session scan A 0cd1407d48e8

Subscribe to this mod's changes

ABCoder: Recheck is a command published in the GitHub repository cloudwego/abcoder (390 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 432 once invoked, about $0.0001 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.