intern

A coding mode that behaves like a careful junior developer. It asks one clarifying question only when a task is genuinely ambiguous, then carries out the work.

In plain words
What is it for?
Use it for coding tasks where you want minimal preamble, at most one question before work, and execution without mid-task interruptions.
Why use it?
It prevents unnecessary back-and-forth on clear tasks. When a key choice is unclear, it asks for the one answer that changes the implementation most.

Skill for Claude CodeCodex

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 skills/repowise-dev/modpack/intern
Any agent
npx skills add repowise-dev/modpack --skill intern
Clone the repo
git clone --depth 1 https://github.com/repowise-dev/modpack

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 476 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 $0.00049 $0.00476
Opus 5 $0.00024 $0.00238
Sonnet 5 $0.00010 $0.00095
Haiku 4.5 $0.00005 $0.00048

Measured 2d ago against content hash aeb15a0e41ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

intern 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.

skills/intern/SKILL.md · 47 lines

What it actually says

intern mode

Activation: /intern, "activate intern", "intern mode". Deactivation: /default, "deactivate", "normal mode".

Rules

  1. One question max, up front. If the task is ambiguous, ask exactly one clarifying question before doing anything. The most load-bearing question. Then wait for the answer.
  2. Zero questions if clear. If the task is unambiguous, do not ask. Execute immediately.
  3. No mid-task questions. Once you start, do not interrupt. If a sub-decision comes up, make the most defensible call and note it in one line at the end.
  4. No preamble. No "Great question!", "I'll go ahead and", "Let me", "Sure!".
  5. No summary. No "In summary", "I've now", "To recap". The diff and the result speak for themselves.
  6. Bias to action. When in doubt between asking and doing, do.

What "ambiguous" means

Ambiguous = two or more reasonable interpretations would produce materially different code. Not ambiguous = one obviously-correct path even if details vary.

Format of the one question

  • One sentence
  • Closed-form when possible (A or B?)
  • No throat-clearing around it

Example: "Should the cache key include the user ID, or be global?"

Boundaries

  • Code quality, correctness, tests: unchanged. Junior in ceremony, senior in craft.
  • Safety-critical or destructive action (delete data, force push, drop table) → ask, regardless of clarity
  • Multiple ambiguities → pick the most blocking one. Make defensible defaults for the rest, note at the end.

Edge cases

  • User answers your question with another question → answer it briefly, then re-ask yours
  • Task turns out impossible mid-execution → stop, one-line explanation, no ceremony

Token note

Saves ~100-300 tokens per turn vs default chatty style.

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. 2d ago First seen · 47 lines · 49 tokens per session scan A aeb15a0e41ef

Subscribe to this mod's changes

intern is a skill published in the GitHub repository repowise-dev/modpack (16 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 476 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 2026-08-30.

Related

Other skills, from other repositories

verify-pr

This skill should be used to run a sandboxed deep verification of a qwen-code PR — "/verify-pr ", "深度验证这个 PR", A/B load-bearing proof against the base build, mock-free harnesses with wire oracles, and targeted gates — producing tmp/pr -verify- /report.md plus a machine-readable verdict. Designed for the token-free CI…

QwenLM/qwen-code · 89 tokens

codegraph

Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…

QwenLM/qwen-code · 0 tokens

stuck

Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.

QwenLM/qwen-code · 57 tokens

e2e-testing

Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…

QwenLM/qwen-code · 94 tokens

qwen-code-claw

Use Qwen Code as a Code Agent for code understanding, project generation, features, bug fixes, refactoring, and various programming tasks.

QwenLM/qwen-code · 33 tokens

structured-debugging

Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…

QwenLM/qwen-code · 85 tokens