diverge SKILL.md skillA
diverge from divergenetwork/diverge is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add divergenetwork/diverge/diverge@git:20261117.df60069Pins git:20261117.df60069 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- divergenetwork/diverge
- Path
diverge-skills/diverge/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261117.df60069, committed Nov 17, 2026
- First version recorded
- Nov 15, 2026
- Size
- 17,371 bytes
- Repository stars
- 10
- License
- MIT
The index and core of the Diverge skills. Load this FIRST for any task that touches Diverge — the `diverge` CLI, a Diverge daemon, provider, identities, agents, agent templates, standalone / dependency / connected tools, images, volumes, the vault, accounts, roles, grants, events, logs, remote daemons, relays, or the diverge-viewer viewer — and load it AGAIN after each such task finishes. It explains the concepts, the shape of the CLI (`diverge run <family> <request> [BODY]`, `request-schema`…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Diverge: index and core Diverge runs AI agents and their tools as containers. A **daemon** holds every record (agents, tools, accounts, secrets, logs) and is the only thing a client talks to; a **provider** runs the containers for it; an **issuer** says who everyone is. You operate all of it from outside, through one program: the `diverge` CLI. ## Protocol: how to use the Diverge skills Follow this for every Diverge task. 1. **Load this skill first.** Do not run a `diverge` command for a new task before reading it. 2. **Load exactly one sub-skill**: the one the table in "Which skill to load" names for the task. Do the task from that skill. 3. **When the task is done, load `diverge` again** before starting the next Diverge task, even if the next task looks similar. The next task may belong to a different skill, and this index is how you find out. If one user request spans several skills (for example "make a volume, then an agent that mounts it"), split it into tasks and run the protocol once per task. ## Concepts | Term | What it is | |---|---| …
Read the whole file at its exact version.
How to install
claude plugin marketplace add https://markdownregistry.com/mp/a/art_h6to2rlekmngdlgg/cc5ac1488d17443fc094e756e821b0d4e73307fd61f4cbac30711c495e04ccae.json
Then /plugin install diverge@markdownregistry-h6to2rlekmngdlgg in Claude Code. It installs git:20261117.df60069, the one graded A here, pinned to the commit it was graded at, and leaves it there.
mdr add divergenetwork/diverge/diverge@sha256:cc5ac1488d17443fThe line at the top of this page pins the label git:20261117.df60069, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_h6to2rlekmngdlgg)
1 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in divergenetwork/diverge/diverge since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of diverge from somewhere else? Ask it: where did my diverge come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 5 versions of this file, between Nov 15, 2026 and Nov 17, 2026, more than one a day.
Watch this file (sign in, one email per new version)
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261117.df60069 latest | 2026-11-17 | df60069 | 17,371 B | A | view · diff |
| git:20261117.e14d2b4 | 2026-11-17 | e14d2b4 | 16,649 B | A | view · diff |
| git:20261117.ce06acf | 2026-11-17 | ce06acf | 16,535 B | A | view · diff |
| git:20261117.612f4fc | 2026-11-17 | 612f4fc | 16,275 B | A | view · diff |
| git:20261115.baf5b74 | 2026-11-15 | baf5b74 | 16,279 B | A | view |
Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.
Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml
It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.
Installed this file, say at .claude/skills/diverge/SKILL.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (17371 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
divergenetwork/diverge · 10 stars · license MIT · pushed 2026-11-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_h6to2rlekmngdlgg GET https://markdownregistry.com/api/v1/resolve?ref=divergenetwork/diverge/diverge GET https://markdownregistry.com/api/v1/blob/cc5ac1488d17443fc094e756e821b0d4e73307fd61f4cbac30711c495e04ccae
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from divergenetwork/diverge
Every file in divergenetwork/diverge