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/yonatangross/orchestkit/release-syncnpx skills add yonatangross/orchestkit --skill release-syncgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/release-sync)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/release-sync"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/release-sync.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 | $0.00062 | $0.01482 |
| Opus 5 | $0.00031 | $0.00741 |
| Sonnet 5 | $0.00012 | $0.00296 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
release-sync 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 today.
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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Content Sync
Sync the latest OrchestKit release to external knowledge systems.
CC ≥ 2.1.118 (M122): Sync triggers on the new
claude plugin tagannotated tag (in addition to plaingit tag). The tag's annotation embeds the plugin manifest version, which release-sync uses as the canonical source-of-truth for the version being synced. Seesrc/skills/chain-patterns/references/plugin-tag.md.
What This Does
- Reads the latest CHANGELOG entry, CLAUDE.md, and hook README
- Updates the OrchestKit NotebookLM KB notebook with fresh sources
- Ingests the release digest into HQ Knowledge Base (if available)
- Optionally generates a new podcast from the updated notebook
Prerequisites
- MCP servers:
notebooklm-mcpand/orhq-content - NotebookLM notebook ID stored in
.claude/release-sync-config.json
Step 1: Detect Version and Read Sources
# Read current version from CLAUDE.md
version = Grep(pattern="Current.*\\d+\\.\\d+\\.\\d+", path="CLAUDE.md")
# Read CHANGELOG — extract latest release section
changelog = Read("CHANGELOG.md", limit=80)
# Read hook architecture summary
hook_readme = Read("src/hooks/README.md", limit=100)
# Read CLAUDE.md for project overview
claude_md = Read("CLAUDE.md")
Step 2: Load Config
config = Read(".claude/release-sync-config.json")
# Expected format:
# {
# "notebooklm_notebook_id": "0a05e680-e33b-4d8c-94b2-5df26a1af329",
# "hq_kb_project": "orchestkit"
# }
If config doesn't exist, prompt user:
AskUserQuestion(questions=[{
"question": "NotebookLM notebook ID for OrchestKit KB?",
"header": "Configuration",
"options": [
{"label": "Use default", "description": "OrchestKit v7 — Complete KB (0a05e680...)"},
{"label": "I'll provide", "description": "Enter a custom notebook ID"}
]
}])
Step 2b: Choose Sync Targets
Ask for the four target values: notebooklm, hq_kb, slack, notes.
# Skip the form when targets are explicit:
# /ork:release-sync --targets=notebooklm,slack → skip, use those
#
# Otherwise ask. This used to prefer an ork-elicit MCP form and fall back to
# AskUserQuestion; the server was retired (EPIC C mechanism 11) because
# AskUserQuestion is the CC-native surface for this and a permanent MCP tool
# slot to restate it was the parallel mechanism. One path now.
#
# ALL targets default to False — OrchestKit is open-source and these targets
# (notebook IDs, HQ KB, Slack) are user-private infrastructure the plugin
# cannot assume is configured. The user explicitly opts in.
targets = {
"notebooklm": ask_yn("Push to NotebookLM?", default=False),
"hq_kb": ask_yn("Push to HQ KB?", default=False),
"slack": ask_yn("Announce in Slack?", default=False),
"notes": ""
}
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.
- today First seen · 175 lines · 62 tokens per session scan A 2d735a317311
release-sync is a skill published in the GitHub repository yonatangross/orchestkit (228 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 1,482 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 2026-09-05.
Other skills, from other repositories
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
transformer-attention
Use when reasoning about Transformer self-attention, multi-head attention, positional encoding, masked decoder attention, or why attention replaced recurrence/convolutions in sequence models; not for generic NLP or unrelated attention topics.
openkb
Use when the user asks about content in their OpenKB knowledge base — research topics, concepts compiled from their documents, cross-document synthesis — or mentions openkb, an .openkb/ directory, or a wiki/ tree generated by openkb. The user may invoke you from any working directory; the active KB resolves via openkb…
turbo-quant-gatekeeper
Use for semantic-memory TurboQuant candidate acceleration, exact rerank, vector artifact lifecycle, and fallback receipts.
disable-model-invocation
A skill that cannot be invoked by the model.
langchain-orchestration
Comprehensive guide for building production-grade LLM applications using LangChain's chains, agents, memory systems, RAG patterns, and advanced orchestration.