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 skills add asfbay-bit/opchain-skills --skill oc-updategit clone --depth 1 https://github.com/asfbay-bit/opchain-skillsWrote 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/asfbay-bit/opchain-skills/oc-update)<a href="https://agentmods.dev/skills/asfbay-bit/opchain-skills/oc-update"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/oc-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/asfbay-bit/opchain-skills/oc-update"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/oc-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 | $0.00065 | $0.03170 |
| Opus 5.5 | $0.00026 | $0.01268 |
| Sonnet 5.5 | $0.00013 | $0.00634 |
| Haiku 4.5 | $0.00006 | $0.00317 |
Grade A, and why
oc-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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Opchain
On first invocation, read references/orchestrator.md and follow its welcome protocol.
Use the bundled updater for all version checks, downloads, installation, and
verification. It needs Node.js 22.13+; consumer updates also need access to
https://opchain.dev. Source checkout updates work offline.
Resolve scripts/update.mjs relative to this loaded skill's directory;
run it with the consuming repository as the working directory. Do not assume
the user's repository contains Opchain's development scripts or package commands.
Commands
First distinguish an update from a first installation. Check the consuming repo's
.claude/skills, .agents/skills, and legacy .codex/skills for Opchain files.
First recognize an Opchain source checkout: a Git root with
skills/orchestrator.md, skills/oc-checkpoint-protocol/SKILL.md, and both
scripts/sync-skill-bundles.mjs and scripts/sync-plugin-skills.mjs. The updater
auto-detects this layout, including when the local skill links have not been
created yet. Run it normally; source links are supported through this path.
If an update/check request has no repo-local installation, report that fact
and identify the host's plugin manager as the route for a global/plugin update.
Do not run the updater's fresh-install default and silently create a duplicate
local copy. This no-local-install rule excludes the source checkout just described.
An explicit request to install in this repo authorizes the fresh
install commands below.
| Request | Run |
|---|---|
/oc-update, "update Opchain" |
node <skill-dir>/scripts/update.mjs |
/oc-update check, "is an update available?" |
Same command with --check (read-only) |
/oc-update doctor, "which Opchain is this session loading?", "why are there two copies?" |
node <skill-dir>/scripts/update.mjs doctor (read-only; --json for machine output; see below) |
| Update only this repo's Opchain plugins | node <skill-dir>/scripts/update.mjs plugins (--check for read-only) |
| "Add the Opchain plugin to this repo", "use the plugin instead of local skills" | node <skill-dir>/scripts/update.mjs --with-plugins (=ow-tools or =opchain,ow-tools only when named; see Adding plugins) |
| Refresh this Opchain source checkout | Same command; --source explicitly requires source mode |
| Install specifically for Claude or Codex | Add --target=claude or --target=codex |
| Install for both | Add --target=both |
| User specifies another repo | Add --root=<absolute-repo-path> |
What ships with it
29 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/checkpoint-protocol.md 37 KB
- references/orchestrator.md 59 KB
- references/recovery.md 1.8 KB
- scripts/opchain.mjs 828 B runs code
- scripts/runtime/package.json 4.7 KB
- scripts/runtime/scripts/checkpoint.mjs 74 KB runs code
- scripts/runtime/scripts/lib/release-evidence.mjs 18 KB runs code
- scripts/runtime/scripts/lib/telemetry-aggregate.mjs 3.2 KB runs code
- scripts/runtime/scripts/lib/verification-receipt.cjs 15 KB runs code
- scripts/runtime/scripts/opchain.mjs 3.9 KB runs code
- scripts/runtime/scripts/runtime-manifest.json 2.0 KB
- scripts/runtime/scripts/runtime/catalog.json 2.3 KB
- scripts/runtime/scripts/runtime/core.mjs 11 KB runs code
- scripts/runtime/scripts/runtime/evaluation.mjs 6.5 KB runs code
- scripts/runtime/scripts/runtime/evolve.mjs 2.5 KB runs code
- scripts/runtime/scripts/runtime/hindsight.mjs 2.4 KB runs code
- scripts/runtime/scripts/runtime/learning.mjs 9.4 KB runs code
- scripts/runtime/scripts/runtime/licenses/js-yaml.txt 1.1 KB
- scripts/runtime/scripts/runtime/licenses/zod.txt 1.0 KB
- scripts/runtime/scripts/runtime/project.mjs 471 B runs code
- scripts/runtime/scripts/runtime/prompt-engine.mjs 496 KB runs code
- scripts/runtime/scripts/runtime/README.md 9.2 KB
- scripts/runtime/scripts/runtime/scorecard.mjs 1.2 KB runs code
- scripts/runtime/scripts/telemetry.mjs 21 KB runs code
- scripts/runtime/scripts/update-opchain.mjs 70 KB runs code
- scripts/runtime/src/lib/mcp/checkpoint-contract.js 14 KB runs code
- scripts/runtime/src/lib/mcp/checkpoint-store.js 5.2 KB runs code
- scripts/runtime/src/lib/mcp/local-checkpoint-store.js 10 KB runs code
- scripts/update.mjs 70 KB runs code
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 Changed · +112 lines db8b6b16461a
- 26d ago Changed a85ebcce6288
- 29d ago Changed 33789ea11533
- 1mo ago First seen · 111 lines · 65 tokens per session scan A 891c557e4ba6
oc-update is a skill published in the GitHub repository asfbay-bit/opchain-skills (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 65 tokens to every session and 3,170 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 2026-09-15.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…