claims
Claims-based authorization for agents and operations. Grant, revoke, and verify permissions for secure multi-agent coordination. Use when: permission management, access control, secure operations, authorization checks. Skip when: open access, no security requirements, single-agent local work.
- Installs
- 1.1K
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/ruvnet/ruflo --skill claims- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads claims automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Claims Authorization Skill
Purpose
Claims-based authorization for secure agent operations and access control.
Claim Types
| Claim | Description |
|---|---|
read | Read file access |
write | Write file access |
execute | Command execution |
spawn | Agent spawning |
memory | Memory access |
network | Network access |
admin | Administrative operations |
Commands
Check Claim
npx claude-flow claims check --agent agent-123 --claim write
Grant Claim
npx claude-flow claims grant --agent agent-123 --claim write --scope "/src/**"
Revoke Claim
npx claude-flow claims revoke --agent agent-123 --claim write
List Claims
npx claude-flow claims list --agent agent-123
Scope Patterns
| Pattern | Description |
|---|---|
* | All resources |
/src/** | All files in src |
/config/*.toml | TOML files in config |
memory:patterns | Patterns namespace |
Security Levels
| Level | Claims |
|---|---|
minimal | read only |
standard | read, write, execute |
elevated | + spawn, memory |
admin | all claims |
Best Practices
- Follow principle of least privilege
- Scope claims to specific resources
- Audit claim usage regularly
- Revoke claims when no longer needed
Cross-Host Work Claims (federation, v3.40.0+)
Distinct from the authorization claims above: work claims coordinate ownership of a task or resource across agents, and now propagate across a cross-host federation so a claim made on one node is visible to the whole swarm.
Runtime tools (local ledger)
| Tool | Purpose |
|---|---|
claims_claim | Take ownership of an issue/resource (with optional TTL). |
claims_release | Give up a claim you hold. |
claims_handoff / claims_accept-handoff | Transfer a claim to another agent. |
claims_steal / claims_mark-stealable | Work-stealing for stalled claims. |
claims_status / claims_list | Inspect current ownership. |
Federated (cross-host)
Publish claim events into a federation room (federation_bbs_publish) so ownership converges across
hosts. Message types: ClaimIssued / ClaimReleased / ClaimHandoff / ClaimAck.
Rules: one owner per resourceId; first valid ClaimIssued wins (ties → earliest ts, then smallest
from); ClaimReleased or expired TTL frees it; ClaimHandoff only from the current owner; a
coordinator posts ClaimAck naming the authoritative owner.
Before shared work: claim, sync, and proceed only if you are the acknowledged owner. When a claim
must be both cross-host visible and runtime-enforced, mirror the two — publish the federation claim
message and call claims_claim. See the cross-host-federation skill (ruflo-bbs-federation plugin)
for the transport.
Scoping a claim stream to a channel (ADR-386)
By default every claim event lands in the shared swarm stream, where any relay member reads it. To keep a team's ownership ledger separate — or unreadable by the rest of the relay — publish claim messages into a channel instead:
npx ruflo federation channel --action create --name platform-team --visibility private
npx ruflo federation channel --action grant --channel prv:<hex> --pubkey <teammate 64-hex>
npx ruflo federation channel --action publish --channel prv:<hex> \
--type ClaimIssued --payload '{"resourceId":"repo/foo","ttlSeconds":7200}'
npx ruflo federation channel --action read --channel prv:<hex>
Reduction rules are unchanged; only the audience changes. Two caveats before relying on it: a private
channel hides content but not metadata (the relay still sees who published and when), and a claim
nobody outside the channel can read cannot arbitrate against a claim made outside it. If ownership
must be swarm-wide, keep it on the open stream. See the open-federation skill for channel mechanics.
FAQ
What does the claims skill do?
Claims-based authorization for agents and operations. Grant, revoke, and verify permissions for secure multi-agent coordination. Use when: permission management, access control, secure operations, authorization checks. Skip when: open access, no security requirements, single-agent local work.
How do I install claims?
Run npx skills add https://github.com/ruvnet/ruflo --skill claims in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/claims/ (personal) or .claude/skills/claims/ (project).
Which AI agents can use claims?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is claims safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains claims?
It is published by ruvnet in ruvnet/ruflo. It has 1,121 recorded installs.
More from ruvnet/ruflo
swarm-orchestration
ruvnet/ruflo
Multi-agent swarm coordination for complex tasks. Uses hierarchical topology with specialized agents to break down and execute complex work across multiple files and modules. Use when: 3+ files need changes, new feature implementation, cross-module refactoring, API changes with tests, security-related changes, performance optimization across codebase, database schema changes. Skip when: single file edits, simple bug fixes (1-2 lines), documentation updates, configuration changes, quick exploration.
agent-arch-system-design
ruvnet/ruflo
Agent skill for arch-system-design - invoke with $agent-arch-system-design
agent-workflow
ruvnet/ruflo
Agent skill for workflow - invoke with $agent-workflow
security-audit
ruvnet/ruflo
Comprehensive security scanning and vulnerability detection. Includes input validation, path traversal prevention, CVE detection, and secure coding pattern enforcement. Use when: authentication implementation, authorization logic, payment processing, user data handling, API endpoint creation, file upload handling, database queries, external API integration. Skip when: read-only operations on public data, internal development tooling, static documentation, styling changes.
github-project-management
ruvnet/ruflo
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available