Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Jerry0022/dotclaude/plugin install devopsWrote 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/jerry0022/dotclaude/auto-update)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/auto-update"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-update/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jerry0022/dotclaude/auto-update"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-update.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00070 | $0.01235 |
| Opus 5.5 | $0.00028 | $0.00494 |
| Sonnet 5.5 | $0.00014 | $0.00247 |
| Haiku 4.5 | $0.00007 | $0.00123 |
Grade A, and why
auto-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 15d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Update
Manually trigger a plugin update with user-facing reporting. The update logic
lives in ss.plugin.update.js (SessionStart hook) — the single source of
truth; this skill captures the state before, runs the hook, and reports.
Constants
PLUGIN_ROOT = {PLUGIN_ROOT} (literal path from the session context; $CLAUDE_PLUGIN_ROOT is empty in the Bash tool)
MARKETPLACE_DIR = ~/.claude/plugins/marketplaces/dotclaude
PLUGIN_SUBDIR = plugins/devops
HOOK_SCRIPT = ${PLUGIN_ROOT}/hooks/session-start/ss.plugin.update.js
Step 0 — Capture current state + channel
- Current version from
<MARKETPLACE_DIR>/<PLUGIN_SUBDIR>/.claude-plugin/plugin.jsonand SHA fromgit -C MARKETPLACE_DIR rev-parse --short HEAD. - Channel pin from
~/.claude/plugins/.channels.json(key = marketplace name, missing/invalid →stable). One channel per MARKETPLACE — a single clone cannot serve two plugins on different channels. --channel <alpha|beta|stable>flag: re-pin by writing the sidecar ({"dotclaude": "beta"}merged into the existing JSON), then continue with the update so the new pin takes effect immediately.- Drift: latest version visible to the pin vs. latest alpha
(
git -C MARKETPLACE_DIR ls-remote --tags origin, numeric compare onalpha/vX.Y.Z/beta/vX.Y.Z/stable/vX.Y.Z/ barevX.Y.Z). - Report:
Currently installed: v{version} ({sha}) — Channel: {channel}, latest visible: v{N}and, when alpha is ahead:(alpha has v{M} available).
Step 1 — Run update hook
node HOOK_SCRIPT --force
--force is required: at SessionStart the hook is throttled by a 6 h cooldown
(#324) and defers cache repairs to a detached child; --force skips both so
the result is complete when this step returns.
The hook does the channel-aware checkout of every marketplace clone, the cache
rebuild, the installed_plugins.json update, a silent verification, and the
Quiet output style refresh. Show its stdout.
Step 2 — Changelog
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.
- 15d ago Changed d4759c8f2c77
- 1mo ago Changed · -62 lines 53afa2c1113c
- 1mo ago Changed 6f329299e2be
- 1mo ago Changed · +17 lines b324d2db3a92
- 2mo ago Changed · +7 lines f0a33840d59d
- 2mo ago First seen · 151 lines · 70 tokens per session scan A efb5f4178742
auto-update is a skill published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 70 tokens to every session and 1,235 once invoked, about $0.0003 per session on Opus 5.5. 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.
auto-update compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| auto-updateJerry0022/dotclaude | Skill | 6 | 11d ago | MIT | A | 70 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |