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 agentmods add commands/biznuts/never-stale/updategit clone --depth 1 https://github.com/biznuts/never-staleWhat 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 | $0.00098 | $0.01767 |
| Opus 5 | $0.00049 | $0.00883 |
| Sonnet 5 | $0.00020 | $0.00353 |
| Haiku 4.5 | $0.00010 | $0.00177 |
Grade A, and why
update 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
never-stale — reconcile after a plugin upgrade
When you upgrade the plugin, projects you opted into earlier keep markers and
CLAUDE.md fences stamped with the version that wrote them. The gate does not
read those stamps (it only checks enabled and the per-event flags), so this drift is
purely cosmetic — but it makes /never-stale:status / :list noisy and lets the
recorded language strings drift apart (e.g. "Traditional Chinese (HK)" vs
"Traditional Chinese (Hong Kong)"). update sweeps your projects and reconciles that
bookkeeping in one pass. It never re-asks your languages and never changes
whether or what the gate fires.
This is bookkeeping, not behavior. If markers reading an older version do not bother you, you do not need to run this at all.
Search root = the path in $ARGUMENTS (ignoring any flag) if given, else the
current working directory. Call it <ROOT>. For a real post-upgrade sweep, pass the
parent that holds your repos (e.g. a path like X:/projects); the default cwd only
reconciles the project you are in.
Dry-run. If $ARGUMENTS contains --dry-run, only print the plan, then STOP
without writing anything.
Step 0 — Determine the installed plugin version
Read ${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json and take its version. Call it
<PV> (the target every reconciled marker/fence is stamped to). If you cannot resolve
${CLAUDE_PLUGIN_ROOT}, find never-stale under your Claude plugins cache and read its
plugin.json; if still unknown, ask the user for the installed version rather than
guessing.
Step 1 — Discover opted-in / legacy projects
Use Glob under <ROOT>:
**/.claude/never-stale.jsonand**/.claude/never-stale.local.json— current markers;**/.claude/hooks/never-stale-reminder.js— legacy v0.5.0 installs.
For each project directory, read the marker(s). If both a team and a local marker exist at the same project, treat the local one as effective (it overrides), but report both — reconcile each file that needs it.
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.
- 2d ago First seen · 127 lines · 98 tokens per session scan A 08077faebd6b
update is a command published in the GitHub repository biznuts/never-stale (2 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,767 once invoked, about $0.0005 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.