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 sidclawhq/platform --skill openclaw-skillgit clone --depth 1 https://github.com/sidclawhq/platformWrote 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/sidclawhq/platform/openclaw-skill)<a href="https://agentmods.dev/skills/sidclawhq/platform/openclaw-skill"><img src="https://agentmods.dev/badge/skills/sidclawhq/platform/openclaw-skill/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/sidclawhq/platform/openclaw-skill"><img src="https://agentmods.dev/badge/skills/sidclawhq/platform/openclaw-skill.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 | $0.00027 | $0.00722 |
| Opus 5.5 | $0.00011 | $0.00289 |
| Sonnet 5.5 | $0.00005 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
sidclaw-governance 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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SidClaw Governance
You have SidClaw governance enabled. Every tool call is evaluated against security policies before execution.
Source code: https://github.com/sidclawhq/platform — the SDK (@sidclaw/sdk) is open-source under Apache 2.0. You can audit the proxy code at packages/sdk/src/mcp/.
How governance affects your behavior
When you use a tool, the SidClaw policy engine evaluates whether the action is allowed. There are three possible outcomes:
1. ALLOWED
The tool executes normally. No changes to your behavior needed. You may see a brief note in the tool response confirming governance was applied.
2. APPROVAL REQUIRED
The tool call is paused pending human review. You will receive an error response containing:
type: "approval_required"approval_request_id: the ID of the pending approvalreason: why this action requires approval
When this happens:
- Tell the user: "This action requires human approval before I can proceed."
- Share the reason from the policy.
- Direct the user to approve or deny the request in the SidClaw dashboard.
- If the user has the dashboard open, they will see an approval card with full context about what you're trying to do and why it was flagged.
- Do NOT retry the tool call until the user confirms the approval was granted.
3. DENIED
The tool call was blocked by policy. You will receive an error response containing:
type: "action_denied"reason: why this action was blocked
When this happens:
- Tell the user: "This action was blocked by a security policy."
- Share the reason from the policy.
- Do NOT retry the tool call or attempt to work around the block.
- Suggest alternative approaches if possible (e.g., if data export is blocked, suggest viewing the data in the dashboard instead).
Rules
- NEVER ignore governance errors. If a tool call is denied, respect the denial.
- NEVER attempt to circumvent governance by calling tools differently or encoding requests to avoid detection.
- When approval is required, ALWAYS inform the user and wait for their confirmation.
- Treat governance responses as authoritative — they reflect security policies set by the organization.
- If multiple tools are governed, each call is evaluated independently.
What ships with it
1 file 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.
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.
- 1mo ago First seen · 77 lines · 27 tokens per session scan A 7e28a467af77
sidclaw-governance is a skill published in the GitHub repository sidclawhq/platform (15 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 722 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
ziran
ZIRAN is an open-source security testing framework for AI agents. It discovers dangerous tool chain compositions via knowledge graph analysis, detects execution-level side effects (not just text output), and runs multi-phase trust exploitation campaigns that model real attacker behavior.
audit-agents
Audit Claude Code subagents, plugins or Python agent code for dangerous tool chains with ziran audit, explain each finding, propose the narrowest tools fix, and set up an allowlist baseline that fails CI when an agent's tools widen. Use when the user asks whether an agent, subagent or plugin is safe, reviews a change…
triage-findings
Triage a ZIRAN scan result (campaignreport.json) - read the findings, decide fix or accept for each, write justified entries in .ziran/suppressions.yaml, gate CI with ziran ci, and produce SARIF, guardrail policies or proof-of-concept scripts. Use when the user has a ZIRAN result file, a failing ziran ci gate, asks…
set-up-scan
Set up a first ZIRAN security scan of an AI agent - discover its tools, write and check a target config, dry-run the attack plan, then run a scan with a coverage level, phases, LLM rate limits and a cost cap. Use when the user wants to scan or pentest their agent with ZIRAN, connect ZIRAN to a local framework agent or…
docs
ACMI is a universal architectural framework for giving AI agents persistent, real-time context. It replaces fragmented, multi-table database joins with a single, lightning-fast Key-Value engine (Upstash Redis) optimized specifically for LLM context windows.
brain-save
Create and manage governed memories by capturing one fact, decision, pattern, or convention, or by retiring an outdated memory. This is side-effecting and never auto-fires. Use when preserving a durable fact without a full recompile or changing a memory's lifecycle. Trigger with "/brain-save".