nudging

nudging is a skill for Claude Code from jukanntenn/glm-plan-usage. It costs 62 tokens per session (360 once invoked), scanned A, original, MIT.

A skill for finding and planning one small, low-risk code improvement without changing what the software does.

In plain words
What is it for?
Use it to identify one cleanup opportunity, then create a task with a detailed specification and implementation plan.
Why use it?
It provides a controlled way to reduce technical debt incrementally instead of attempting a broad refactor.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to identify one cleanup opportunity, then create a task with…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jukanntenn/glm-plan-usage/nudging
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.

Any agent
npx skills add jukanntenn/glm-plan-usage --skill nudging
Clone the repo
git clone --depth 1 https://github.com/jukanntenn/glm-plan-usage

Made for: Claude Code.

Wrote 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.

agentmods badge for nudging

README.md
[![agentmods](https://agentmods.dev/badge/skills/jukanntenn/glm-plan-usage/nudging.svg)](https://agentmods.dev/skills/jukanntenn/glm-plan-usage/nudging)
Your own site
<a href="https://agentmods.dev/skills/jukanntenn/glm-plan-usage/nudging"><img src="https://agentmods.dev/badge/skills/jukanntenn/glm-plan-usage/nudging.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 360 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00062 $0.00360
Opus 5 $0.00031 $0.00180
Sonnet 5 $0.00012 $0.00072
Haiku 4.5 $0.00006 $0.00036

Measured 6d ago against content hash 23683d6fb920, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

nudging 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.

.claude/skills/nudging/SKILL.md · 40 lines

What it actually says

What this does

Find a single, small improvement in the codebase and plan it. Think of it as paying down technical debt one coin at a time — each nudge makes the code slightly cleaner without any risk to behavior.

Workflow

  1. Scan the codebase for a concrete improvement opportunity. Pick one.
  2. Create a task: fa task create <slug>
  3. Write spec.md in the task directory describing the change.
  4. Write plan.md in the same directory. The plan must be detailed enough that someone unfamiliar with the codebase could execute it without making a single design decision.

Output JSON when done:

{
  "task_id": <task-id>,
  "task_path": "<absolute-path-to-task-directory>"
}

What counts as a nudge

  • Extract a code fragment into a pure function, add type hints, write unit tests
  • Fix naming inconsistencies that hurt readability
  • Simplify equivalent code — remove redundancy or unnecessary complexity
  • Any small, self-contained improvement that leaves the codebase cleaner

This list is not exhaustive — use your judgment.

Rules

  • Each function should do one thing. If you spot one that does two, that is a valid nudge.
  • Never change business logic. The behavior before and after must be identical.
  • Keep the scope small. One nudge per invocation — resist the urge to chain improvements.
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. 6d ago First seen · 40 lines · 62 tokens per session scan A 23683d6fb920

Subscribe to this mod's changes

nudging is a skill published in the GitHub repository jukanntenn/glm-plan-usage (13 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 360 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 2026-08-30.