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.
npx skills add jukanntenn/glm-plan-usage --skill nudginggit clone --depth 1 https://github.com/jukanntenn/glm-plan-usageWrote 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/skills/jukanntenn/glm-plan-usage/nudging)<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>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 | $0.00062 | $0.00360 |
| Opus 5 | $0.00031 | $0.00180 |
| Sonnet 5 | $0.00012 | $0.00072 |
| Haiku 4.5 | $0.00006 | $0.00036 |
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.
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
- Scan the codebase for a concrete improvement opportunity. Pick one.
- Create a task:
fa task create <slug> - Write
spec.mdin the task directory describing the change. - Write
plan.mdin 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.
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 · 40 lines · 62 tokens per session scan A 23683d6fb920
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.