veriswarm

veriswarm is a skill for Claude Code, Codex from veriswarm/veriswarm-sdk. It costs 43 tokens per session (667 once invoked), scanned A, original, MIT.

A security and trust guard for OpenClaw agents, which are software agents that can use tools on a user’s behalf. It removes personal information, checks for prompt injection, controls tool access, and records actions in an audit ledger.

In plain words
What is it for?
Use it to protect messages and tool results, allow or block tools, check trust decisions, restore protected data when writing to real systems, and review or verify the audit trail.
Why use it?
It reduces the chance that private data reaches the language model or that an agent follows malicious instructions or uses an unsafe tool.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Install

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.

agentmods
npx agentmods add skills/veriswarm/veriswarm-sdk/openclaw-plugin
Any agent
npx skills add veriswarm/veriswarm-sdk --skill openclaw-plugin
Clone the repo
git clone --depth 1 https://github.com/veriswarm/veriswarm-sdk

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for veriswarm

README.md
[![agentmods](https://agentmods.dev/badge/skills/veriswarm/veriswarm-sdk/openclaw-plugin.svg)](https://agentmods.dev/skills/veriswarm/veriswarm-sdk/openclaw-plugin)
Your own site
<a href="https://agentmods.dev/skills/veriswarm/veriswarm-sdk/openclaw-plugin"><img src="https://agentmods.dev/badge/skills/veriswarm/veriswarm-sdk/openclaw-plugin.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 667 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00667
Opus 5 $0.00022 $0.00333
Sonnet 5 $0.00009 $0.00133
Haiku 4.5 $0.00004 $0.00067

Measured 5d ago against content hash b3d1b86109b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

veriswarm 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 5d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (src/client.ts, src/index.ts, src/secret_tripwire.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

openclaw-plugin/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VeriSwarm Guard for OpenClaw

Protect your OpenClaw agent with VeriSwarm's full trust and security suite.

What it does

Automatic (transparent, no agent action needed):

  • Strips PII (names, emails, phones, SSNs, addresses, credit cards) from messages before they reach the LLM
  • Strips PII from tool outputs before the agent sees them
  • Scans tool outputs for prompt injection attempts
  • Enforces tool allowlists and blocklists
  • Logs every action to VeriSwarm's tamper-proof audit ledger

Tools the agent can use:

  • veriswarm_check_trust — Get current trust scores
  • veriswarm_check_decision — Ask if an action should be allowed
  • veriswarm_rehydrate — Restore PII tokens when writing to real systems
  • veriswarm_guard_status — Check active protections
  • veriswarm_get_credentials — Issue a portable trust credential
  • veriswarm_verify_credential — Verify another agent's credential
  • veriswarm_query_ledger — Search the audit trail
  • veriswarm_verify_chain — Verify audit chain integrity

Setup

  1. Get a free VeriSwarm API key at https://veriswarm.ai
  2. Set VERISWARM_API_KEY in your OpenClaw environment
  3. Install the plugin:
    openclaw plugins install veriswarm
    
  4. Guard is now active. PII is automatically stripped from all messages and tool I/O.

Configuration

In your OpenClaw config:

{
  plugins: {
    entries: {
      veriswarm: {
        enabled: true,
        config: {
          apiKey: "vsk_your_key_here",
          // All protections on by default:
          piiEnabled: true,
          policyEnabled: true,
          injectionScan: true,
          auditEnabled: true,
          // Optional: block specific tools
          blockedTools: ["dangerous_tool"],
        }
      }
    }
  }
}

Rehydrating PII

When the agent needs to write tokenized data back to a real system:

  1. Tool output arrives with tokens: "Customer [VS:PERSON:a1b2c3] at [VS:EMAIL:d4e5f6]"
  2. Agent processes data (LLM never sees real PII)
  3. Agent calls veriswarm_rehydrate to restore real values for the write
  4. Every rehydration is logged for audit compliance

Read the full file on GitHub · 81 lines

Changes

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.

  1. 5d ago First seen · 81 lines · 43 tokens per session scan A b3d1b86109b5

Subscribe to this mod's changes

veriswarm is a skill published in the GitHub repository veriswarm/veriswarm-sdk (2 stars, last pushed 12d ago), licensed MIT. It adds 43 tokens to every session and 667 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

orloj-generator

Interactive scaffold generator for Orloj multi-agent systems. Use this skill whenever someone wants to create, set up, scaffold, bootstrap, or generate an Orloj agent system, pipeline, swarm, or hierarchy. Also trigger when users mention "orlojctl init", ask how to get started with Orloj, want to build a multi-agent…

OrlojHQ/orloj · 168 tokens

air-blackbox-sales-agent

AIR Blackbox's autonomous sales prospecting agent. Finds Python AI projects on GitHub that need EU AI Act compliance, identifies the right person to contact (CEO, CTO, lead maintainer), runs a free compliance scan, and drafts personalized outreach emails that convert to engagement. The sales flow: free scan as the…

airblackbox/airblackbox · 248 tokens

harness

End-to-end workflow orchestrator. Walks the 11-phase pipeline, invoking each phase skill in order inside an internal loop, yielding at consent gates (/approve-direction, /approve-swarm, /grant-commit), and exiting cleanly on yield/failure/done. Decides swarm-vs-solo at Phase 6. Auto-loops /tdd on integrate failures…

friedbotstudio/baseline · 110 tokens

triage

Triage an incoming request — pick the workflow entry phase (intake / spec / tdd / chore) and record the workflow statefile that the Track Guard reads.

friedbotstudio/baseline · 37 tokens

memory-sync

Review the auto-extracted candidates in .claude/memory/pending.md and commit keepers to the canonical memory files (landmarks.md, libraries.md, decisions.md, landmines.md, conventions.md, pending-questions.md, backlog.md). Invoke at session start when the SessionStart hook reports pending candidates, or any time…

friedbotstudio/baseline · 99 tokens

interpret-results

Interprets AIR Blackbox scan results and maps findings to specific EU AI Act articles, recitals, and remediation steps. Use when the user has scan output and wants to understand what to fix, why it matters, or how to prioritize.

airblackbox/airblackbox · 49 tokens