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 agentmods add skills/iblai/api/iblai-api-agent-sandboxnpx skills add iblai/api --skill iblai-api-agent-sandboxgit clone --depth 1 https://github.com/iblai/apiWrote 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/iblai/api/iblai-api-agent-sandbox)<a href="https://agentmods.dev/skills/iblai/api/iblai-api-agent-sandbox"><img src="https://agentmods.dev/badge/skills/iblai/api/iblai-api-agent-sandbox.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.02307 |
| Opus 5 | $0.00030 | $0.01154 |
| Sonnet 5 | $0.00012 | $0.00461 |
| Haiku 4.5 | $0.00006 | $0.00231 |
Grade A, and why
iblai-api-agent-sandbox scanned grade A with 1 finding 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.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST \ How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iblai-api-agent-sandbox
Wire an agent to a Claw sandbox instance, manage the available instances, push config and run health/connectivity checks, and set the model the agent's workspace uses. Use when connecting an agent to a sandboxed workspace.
Auth & conventions
- Base URL:
https://api.iblai.app - Header:
Authorization: Api-Token $IBLAI_API_KEYon every request. - Prefix: paths shown as
…are underhttps://api.iblai.app/dm/api/ai-mentor— the/dmgateway routes to the Data Manager service. (…/api/ai-agent/…is an accept-only alias for the same routes.) - Path vars:
{org}=$IBLAI_ORG,{username}=$IBLAI_USERNAME,{mentor}= the agent's unique id (a UUID, e.g.d17dc729-60fd-4363-81a0-f67d9318b03e).{id}onclaw/instances/andclaw/model-providers/is the integer primary key. - Not connected yet? Run
/iblai-api-loginfirst to populateIBLAI_ORG,IBLAI_USERNAME, andIBLAI_API_KEY.
Reads
Instances
- GET
…/orgs/{org}/claw/instances/— list registered Claw instances. - GET
…/orgs/{org}/claw/instances/{id}/— retrieve one instance (status,claw_version, last health/pairing).
Model providers
- GET
…/orgs/{org}/claw/model-providers/— list the org's model-provider blocks. - GET
…/orgs/{org}/claw/model-providers/{id}/— retrieve one provider block.
Agent config
- GET
…/orgs/{org}/mentors/{mentor}/claw-config/— the agent's connected instance + push status (404 = not connected). - GET
…/orgs/{org}/mentors/{mentor}/agent-config/— agent workspace config (includes current model). - GET
…/orgs/{org}/users/{username}/mentor-llms/?mentor_id={mentor}— available model options.
Writes
Instances
- POST
…/orgs/{org}/claw/instances/— register an instance:{ "name": "string", "claw_type": "openclaw | ironclaw | nemoclaw", "server_url": "https://claw.example.com", "gateway_token": "string (write-only)", "connection_params": { "device_identity": {} }, "auth_headers": {}, "deployment_backend": "backend id (optional)" } - PATCH
…/claw/instances/{id}/— edit (send only changed writable keys:name,claw_type,server_url,gateway_token,connection_params,auth_headers,deployment_backend). - DELETE
…/claw/instances/{id}/— delete instance. Destructive — confirm with the user first. - POST
…/claw/instances/{id}/health-check/— queue a health check (returns202; poll the instance forlast_health_status). - POST
…/claw/instances/{id}/test-connectivity/— TLS reachability + health check. - POST
…/claw/instances/{id}/refresh-version/— detectclaw_versionfrom the instance handshake. - POST
…/claw/instances/{id}/request-pairing/— queue a device-pairing request (pending request expires ~5 min). Outward-facing — confirm with the user first. - POST
…/claw/instances/{id}/push-providers/— push all enabled model providers to the instance. Outward-facing — confirm with the user first. - POST
…/claw/instances/{id}/security-audit/— run a security audit (OpenClaw only). Outward-facing — confirm with the user first.
What ships with it
2 files 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.
- 5d ago First seen · 167 lines · 60 tokens per session scan A 1c81925f8d8a
iblai-api-agent-sandbox is a skill published in the GitHub repository iblai/api (15 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 2,307 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
vindicate
Use when the user wants to write, add, fix, stabilize (flaky), refactor, run, or audit Playwright browser tests, draft requirements/stories from a recording (no tests), find test-coverage gaps, scaffold a Playwright project, or set up Playwright CI. Vindicate's guided workflow for grounded, conformant Playwright test…
figma-create-design-system-rules
Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server…
confluence-assistant
Central hub for Confluence operations - routes requests to specialized skills. ALWAYS use when user mentions confluence, wiki, or Atlassian wiki operations.
megalinter-check
Collect MegaLinter lint errors for the current repository. Use when the user wants to know if the code passes linting, why the MegaLinter CI job fails, or before/after fixing lint errors. Two modes - watch a CI job (GitHub Actions, GitLab CI, Azure Pipelines, Bitbucket Pipelines) and parse its logs, or run MegaLinter…
assistant
Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.
design-assessment
WHAT - Evidence-based design-unit assessment orchestrated by project-assessment. Evaluates visual hierarchy, UX friction, interaction, a11y, responsiveness, design-system compliance, and distinctiveness with severity/confidence evidence citations. Reuses project-assessment-evidence semantics — no second framework.