Install
$ agentstack add skill-nomograph-ai-rune-rune ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README — it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
rune -- registry manager
Manages skills, agents, and rules across projects via git-based registries. Skills are markdown files in .claude/skills/ that teach agents how to perform workflows. Agents are subagent definitions in .claude/agents/. Rules are conditional instructions in .claude/rules/. rune keeps them current.
When to invoke
- **After modifying any file in
.claude/skills/,.claude/agents/, or
.claude/rules/**: run rune check to detect drift. If drifted, ask the user if they want to push.
- At session start: muxr pre_create hook runs
rune syncautomatically.
You do not need to run sync yourself.
- When the user asks about skills: run
rune lsto show status. - When adding an item:
rune add --from [-t type].
Commands
rune check # show drift for all items
rune check --file PATH # check a specific file (used by hook)
rune sync # pull updates from all registries
rune push # push local changes back to registry
rune add --from # add a skill from a registry
rune add -t agent # add an agent
rune add -t rule # add a rule
rune ls # list items and sync status
rune init # create .claude/rune.toml for this project
rune setup # one-time: create config + install hook
After modifying a skill file
The PostToolUse hook fires automatically and shows drift. When you see drift output, present it to the user:
"I updated .md. It now differs from the registry. Want me to push this change upstream so other projects get it?"
Wait for explicit approval before running rune push . This is an external write -- the same approval gate as git push.
Output format
tidy CURRENT registry: public
voice DRIFTED local is newer registry: private
mirror MISSING registry: public
- CURRENT: local matches registry
- DRIFTED: local and registry differ (direction shown)
- MISSING: in manifest but not on disk (run sync)
- REGISTRY MISSING: in manifest but not in registry
Organizing an existing .claude/ directory with rune
If the user has skills, agents, or rules that are not yet managed by rune, help them migrate:
- Check if rune is set up: look for
.claude/rune.toml. If missing,
run rune init.
- For each file in
.claude/skills/,.claude/agents/,.claude/rules/:
- If it came from a registry, add it to the manifest with
rune add --from [-t type].
- If it was written locally and should be shared, suggest creating
a registry (a git repo with skills/, agents/, rules/ dirs) and using rune push after adding it to the manifest.
- Files in
.claude/commands/should be moved to.claude/skills/.
Claude Code merged commands into skills in v2.1.3. Move the file to a skill directory: mkdir -p .claude/skills/ then mv .claude/commands/.md .claude/skills//SKILL.md.
- Run
rune syncto verify everything resolves.
Configuration
~/.config/rune/config.toml-- registries (name, url, branch).claude/rune.toml-- per-project manifest (skills, agents, rules)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: nomograph-ai
- Source: nomograph-ai/rune
- License: MIT
- Homepage: https://gitlab.com/nomograph/rune
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.