Skip to content
FunCoding

Search

Search docs, Skills and MCP

qoder-delegate

Delegate a coding task to the Qoder CLI (`qodercli`) as a background implementer, then review its diff and land it yourself. Use this whenever the user asks to have Qoder implement, fix, refactor, or run a queue of coding tasks while the orchestrator remains the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants code written directly without delegation.

代码质量与审查2.3kskills/qoder-delegate/SKILL.md

Install

Send this to Claude Code, Codex or Cursor. The agent checks the Skill for safety first and installs it only after you confirm.

读取 https://funcoding.ai/skills/amelnagdy/delegate-skills/qoder-delegate/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

Qoder Delegate

You are the orchestrator. Delegate one bounded coding task to a separate implementer - Qoder CLI - then review what it produced and land it yourself. You write the brief and own the judgment; Qoder edits the working tree in its session; you verify and commit.

The loop needs only shell and file access, so any comparable orchestrator can drive it.

When NOT to use this

  • The task is small enough to do inline; delegation overhead is not worth it.
  • qodercli is not installed or authenticated.
  • You want to write the code yourself or need only an interactive Qoder session.

Prerequisites (check once)

command -v qodercli
qodercli --version
qodercli --list-models

If the binary is missing, install it from Qoder's official Quick Start. Authenticate with qodercli login, or set QODER_PERSONAL_ACCESS_TOKEN for automation. A successful --list-models confirms the current account can return its live model catalog.

Choose model and context window

Qoder's available models can change. If the human requests a model, use its exact current value from qodercli --list-models; never invent or pin a catalog entry. Otherwise omit --model and let Qoder use its current default.

--context-window <n> is optional. Pass a positive integer only when the human requests a size or the task needs an explicit budget. Qoder applies it only to supported models; surface an unsupported model/size error instead of silently choosing another value.

The loop

Run these five steps per task. Steps 1, 4, and 5 require judgment; 2 and 3 are mechanical.

1. Write the brief

Qoder sees the brief plus what it can inspect in the workspace, not this chat. Include the goal, current state, what to change, what to leave untouched, the project's actual gates, and a closing report contract. Tell Qoder not to commit. Keep one task per brief. See references/writing-the-brief.md.

2. Dispatch

Use the bundled relay. It wraps Qoder's non-interactive stream-json mode and writes result.json. <skill-dir> is the installed folder containing this SKILL.md.

node "<skill-dir>/scripts/relay.mjs" --brief brief.txt --cd /path/to/repo
# choose a live model:                 add --model "<value from qodercli --list-models>"
# request a supported context window: add --context-window 32768
# resume the latest session:          add --resume-last  # delta brief only
# resume a specific session:          add --resume <id>  # delta brief only
# see every option:                   node .../relay.mjs --help

Implementation runs default to Qoder's auto permission mode. The relay never bypasses permissions unless the caller explicitly requests it, and it never commits. See references/dispatch-and-poll.md.

3. Wait for completion

The relay blocks until Qoder exits. Run it with the orchestrator's background-command facility, or background it in the shell and wait for result.json. Completion means the process exited and the file contains a status; do not trust a progress display.

A pre-run usage error exits 2 and writes no result. Missing qodercli exits 127 and writes status: "qoder_unavailable" with installation guidance.

Native Windows relay launch is not yet verified; do not claim it until a native Windows smoke passes.

4. Review - do not trust the self-report

Treat Qoder's final message and gate outcomes as claims:

  • Re-run the project's gates yourself.
  • Read the diff against the brief, starting with touchedFiles.
  • Check any --add-dir workspaces separately; their changes are not in the primary tree report.
  • Run relevant guard skills if installed.
  • Round-trip migrations and grep for dangling references after removals or renames.

See references/review-and-land.md.

5. Land it

The implementer edits; the orchestrator commits. Commit only after the gates pass and the diff holds. If rework is needed, send a delta brief with --resume-last or --resume <id>, then review again.

Permission model

Qoder print mode cannot show approval prompts. The relay defaults to auto, which makes non-interactive allow/deny decisions. default can deny actions that would require a prompt; accept_edits permits workspace edits but may deny shell actions; dont_ask fails closed; plan maps to default plus Qoder's Plan work state; and bypass_permissions is for explicitly trusted runs only.

Qoder falls back to default when a non-default mode is requested outside a trusted directory. Check actualPermissionMode in result.json; no requested mode replaces diff review.

Authorization model

Delegation is something the human opts into. Once they ask for it, landing verified, gate-passing work is the contract. Two limits remain: surface, do not absorb (report Qoder's design decisions and non-blocking deviations) and stop for scope changes (ask before expanding beyond the brief). See references/review-and-land.md.

References

Similar Skills

claude-api
anthropics/skills180k

claude-api

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

Code quality & review

ponytail-review
DietrichGebert/ponytail158k

ponytail-review

Quality review of a change: is the logic right, is it safe, does it hold under real load, is risky code tested, is it fast enough, and is every line needed. Reads the connected code, not only the diff. Each finding is explained in plain English. Use for "review this", "code review", "review the last commit", "review my PR", "is this over-engineered", /ponytail-review.

Code quality & review

code-review-and-quality
addyosmani/agent-skills103k

code-review-and-quality

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch. Use when asked to review a diff or a pull request, even when the diff is pasted inline.

Code quality & review

documentation-and-adrs
addyosmani/agent-skills103k

documentation-and-adrs

Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

Code quality & review

code-simplification
addyosmani/agent-skills103k

code-simplification

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

Code quality & review

understand
Egonex-AI/Understand-Anything86k

understand

Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships

Code quality & review