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/prabhdeepsingh/claude-plugins/releasegit clone --depth 1 https://github.com/PrabhdeepSingh/claude-pluginsWhat 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 | $0.00059 | $0.01274 |
| Opus 5 | $0.00030 | $0.00637 |
| Sonnet 5 | $0.00012 | $0.00255 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
release 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/release — the five-home sync, done right every time
Why this exists: installed copies of the plugin are pinned — a change on main reaches nobody until the version is bumped and users run /plugin marketplace update. And the plugin's description lives in five files that must move together. Both halves of that have failed before (two releases of marketplace drift; one behavior fix that never got a bump). This command is the procedure.
If $ARGUMENTS is tag, skip straight to Phase 5 (the PR already merged). Otherwise run Phases 1–4 in order.
Guard first. This command releases the claude-plugins repo itself:
[ -f .claude-plugin/marketplace.json ] && [ -d sonu/skills ] \
&& echo "OK: claude-plugins repo" || echo "STOP: not the claude-plugins repo"
Phase 1 — What changed, and what bump does it earn
git log $(git describe --tags --abbrev=0 2>/dev/null || echo origin/main)..HEAD --oneline
git diff origin/main --stat 2>/dev/null | tail -5
CURRENT=$(python3 -c "import json; print(json.load(open('sonu/.claude-plugin/plugin.json'))['version'])")
echo "current version: $CURRENT"
Pick the bump (from $ARGUMENTS if given — the text typed after the command; if that token appears literally or is empty, infer from the diff):
| Change | Bump |
|---|---|
| New skill or command added, or behavior of an existing one meaningfully changed | minor |
| Fix/clarification to existing component, docs, manifests | patch |
| Removed or renamed a component, or changed how users invoke things | major |
Any user-visible change gets a bump. "It's just a wording fix in ship.md" is a behavior change for the model executing it — that exact reasoning skipped a bump once and left every installed copy running the buggy text.
Phase 2 — The five homes, in order
Update each; the version appears in homes 1–2, the plugin description in homes 1–5 (sync the description text only if the component set or a component's pitch changed):
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 · 81 lines · 59 tokens per session scan A dbcf50cbbacc
release is a command published in the GitHub repository PrabhdeepSingh/claude-plugins (3 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 1,274 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.
Other commands, from other repositories
log-time
Log work hours on an Atera ticket.
run-powershell
Execute a PowerShell script on an Atera agent.
eol-report
EOL/EOS risk report — devices, OS versions, and firmware approaching or past end-of-life/end-of-support, prioritized by criticality.
update-ticket
Update fields on an existing Atera ticket.
alert-triage
Triage open Auvik alerts, rank by severity, and recommend dismissals for known noise.
release
Generate changelog, bump version, and create git tag.