agentmods.dev

on

on is a command for coding agents from biznuts/never-stale. It costs 62 tokens per session (1,003 once invoked), scanned A, original, MIT.

A project command that resumes the never-stale reminders after they were paused. It turns the feature back on and reuses the project’s existing languages and rules.

In plain words
What is it for?
Use it when never-stale has been paused and you want its reminders active again; if the project was never configured, use its setup command instead.
Why use it?
It restores automatic compacting and documentation-sync reminders without asking you to configure the project again.

Command

Part of the never-stale plugin — 8 commands, 2 hooks shipped together

not rated 2 1mo ago A scan 62 tokens original MIT
View the source file biznuts/never-stale
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/biznuts/never-stale/on
Clone the repo
git clone --depth 1 https://github.com/biznuts/never-stale

Or install never-stale, the plugin that ships this one along with the rest of its 8 commands, 2 hooks.

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 on

README.md
[![agentmods](https://agentmods.dev/badge/commands/biznuts/never-stale/on.svg)](https://agentmods.dev/commands/biznuts/never-stale/on)
Your own site
<a href="https://agentmods.dev/commands/biznuts/never-stale/on"><img src="https://agentmods.dev/badge/commands/biznuts/never-stale/on.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,003 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 $0.00062 $0.01003
Opus 5 $0.00031 $0.00502
Sonnet 5 $0.00012 $0.00201
Haiku 4.5 $0.00006 $0.00100

Measured 4d ago against content hash 0e589411c4c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

on 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 4d 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.

never-stale/commands/on.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

never-stale — resume this project (on)

on is the other half of the /never-stale:off toggle: it sets the governing marker's "enabled" back to true, re-arming the gate for new sessions. It reuses the languages and the sentinel-fenced CLAUDE.md block that were already there — it asks nothing and writes no new rules.

If the project was never set up (no marker at all), there is nothing to resume — run /never-stale:setup instead, which asks your languages and scaffolds everything.

Project root = the path in $ARGUMENTS if given, else the current working directory. Call it <ROOT>.

Step 1 — Find the governing marker

Walk up from <ROOT> to the nearest ancestor that carries a marker, bounded by the git repo root (same resolution the gate uses):

  1. Start at <ROOT>. At each directory D, check for D/.claude/never-stale.local.json then D/.claude/never-stale.json.
  2. If either exists, that directory governs — stop. (A local marker at D overrides a team marker at the same D.)
  3. Otherwise, if D/.git exists, stop (repo root — no marker).
  4. Else go up to the parent and repeat.

Read whichever marker(s) the governing directory carries. Call it <GOV>.

Step 2 — Decide what to flip

  • No governing marker found → nothing to resume. Tell the user to run /never-stale:setup to opt in, and stop.
  • Effective marker already enabled: true → already active; say so and stop. (If the effective marker is a local one that is already enabled, the project is on regardless of any team marker — say so.)
  • A local marker governs and is enabled: false → this is the paused/vetoing override.
    • If there is also a team marker at <GOV> (i.e. the local one was vetoing an inherited team opt-in), use AskUserQuestion to offer:
      1. Re-enable the local override — set the local marker's "enabled" to true.
      2. Drop the local override — delete <GOV>/.claude/never-stale.local.json so the project falls back to the (enabled) committed team marker. Offer to remove its .gitignore line too.
    • If there is no team marker (the local marker is the only one) → simply set the local marker's "enabled" to true.
  • Only a team marker governs and is enabled: false → set the committed <GOV>/.claude/never-stale.json "enabled" to true. Note that, for teammates, this takes effect once committed and pulled.

Read the full file on GitHub · 76 lines

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. 4d ago First seen · 76 lines · 62 tokens per session scan A 0e589411c4c8

Subscribe to this mod's changes

on is a command published in the GitHub repository biznuts/never-stale (2 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,003 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 2026-08-31.

Building agentsanthropicautomationclaudeclaude-codeclaude-code-plugindeveloper-tools
Related

Other commands, from other repositories

learn

Force claude-smart to extract learnings from this session now.

ReflexioAI/claude-smart · 14 tokens

init

Install the formatters this repository needs, with every command visible before it runs.

azrtydxb/procoder · 16 tokens

brand-generate

Generate an on-brand document from a saved Brand Profile.

ferdinandobons/brand-docs · 0 tokens

genshijin-compress

Markdown・テキストファイルを原始人形式へ安全圧縮.

InterfaceX-co-jp/genshijin · 17 tokens

save

Save this conversation as a new or existing reusable context.

XTSoftwareLabs/neatcontext-plugins · 10 tokens

standup

Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.

skullninja/coco-workflow · 21 tokens