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 skills/jerry0022/dotclaude/promotenpx skills add Jerry0022/dotclaude --skill promotegit clone --depth 1 https://github.com/Jerry0022/dotclaudeWrote 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/promote)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/promote"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/promote.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 | $0.00122 | $0.01556 |
| Opus 5 | $0.00061 | $0.00778 |
| Sonnet 5 | $0.00024 | $0.00311 |
| Haiku 4.5 | $0.00012 | $0.00156 |
Grade A, and why
promote 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release — Channel Promotion
Promote a shipped version to a higher channel. Ship publishes every version
to alpha autonomously; this skill is the deliberate half of the ring
model (spec: docs/superpowers/specs/2026-07-11-tag-channel-system-design.md).
CRITICAL —
cwdis required on every MCP tool call. The ship MCP server runs in the plugin directory, NOT the target repo. Everyship_promotecall MUST includecwdset to the current working directory of this Claude session.
Step 0 — Load deferred MCP schema
ship_promote may be deferred. Load it first:
ToolSearch({ query: "select:mcp__plugin_devops_dotclaude-ship__ship_promote", max_results: 5 })
If the tool is not registered → STOP and report (do NOT fall back to manual
git tag — the promotion guards live in the tool).
Step 1 — Gather channel state
git ls-remote --tags origin
Parse tag names (alpha/vX.Y.Z, beta/vX.Y.Z, stable/vX.Y.Z, bare
vX.Y.Z = stable alias) and compute the latest version per channel by
numeric version comparison — never lexicographic, never
--sort=v:refname across channel prefixes.
Render ONE line:
Channels: alpha v0.117.0 · beta v0.114.0 · stable v0.112.0
If alpha has never shipped a channel tag → report "no channel tags yet — ship something first" and stop.
Step 2 — Ask which promotion
Precompute only the meaningful promotions (source strictly ahead of target). Present via AskUserQuestion, recommended option first:
alpha vX → beta(Recommended when alpha > beta)beta vY → stablealpha vX → stable (fast-track)— legitimate skip; beta is optional- Abbrechen
If NO promotion is meaningful (all channels equal) → report "all channels
are at vX — nothing to promote" and stop. Never promote autonomously, even
with --autonomous in the trigger.
Step 3 — Execute
Single-step promotion:
ship_promote({ version: "0.117.0", from: "alpha", to: "beta", cwd: "<cwd>" })
Fast-track = TWO sequential calls so the ring invariant (stable ⊆ beta ⊆ alpha) always holds:
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 · 140 lines · 122 tokens per session scan A 681bb8e35bff
promote is a skill published in the GitHub repository Jerry0022/dotclaude (5 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 1,556 once invoked, about $0.0006 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 skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.