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 holaboss-ai/holaOS --skill app-builder-sdkgit clone --depth 1 https://github.com/holaboss-ai/holaOSWrote 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/holaboss-ai/holaos/app-builder-sdk)<a href="https://agentmods.dev/skills/holaboss-ai/holaos/app-builder-sdk"><img src="https://agentmods.dev/badge/skills/holaboss-ai/holaos/app-builder-sdk/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/holaboss-ai/holaos/app-builder-sdk"><img src="https://agentmods.dev/badge/skills/holaboss-ai/holaos/app-builder-sdk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 461 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 82 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 82 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 472 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00047 | $0.10500 |
| Opus 5 | $0.00023 | $0.05250 |
| Sonnet 5 | $0.00009 | $0.02100 |
| Haiku 4.5 | $0.00005 | $0.01050 |
Grade A, and why
app-builder-sdk 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 9d 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 -sS http://127.0.0.1:8080/api/v1/capabilities/runtime-tools/integrations/catalog | jq '.provider_ids' The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
44 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.
- reference/gcalendar-events/app.ts 7.4 KB runs code
- reference/gcalendar-events/e2e.ts 13 KB runs code
- reference/gcalendar-events/provider.ts 296 B runs code
- reference/github-workflow/app.ts 5.5 KB runs code
- reference/github-workflow/provider.ts 245 B runs code
- reference/pinterest-publishing/app.ts 4.6 KB runs code
- reference/pinterest-publishing/provider.ts 271 B runs code
- reference/slack-messaging/app.runtime.yaml 964 B
- reference/slack-messaging/app.ts 8.1 KB runs code
- reference/slack-messaging/e2e-bearer.ts 3.4 KB runs code
- reference/slack-messaging/e2e.ts 14 KB runs code
- reference/slack-messaging/manifest.ts 968 B runs code
- reference/slack-messaging/provider.ts 241 B runs code
- reference/slack-messaging/run.ts 3.3 KB runs code
- reference/slack-messaging/server.ts 2.8 KB runs code
- reference/telegram-messaging/app.ts 6.7 KB runs code
- reference/telegram-messaging/e2e.ts 9.0 KB runs code
- reference/telegram-messaging/provider.ts 256 B runs code
- sdk-package/package.json 1.6 KB
- sdk-package/README.md 10 KB
- sdk-package/README.txt 10 KB
- sdk-package/src/app.ts 14 KB runs code
- sdk-package/src/bridge-transports/bearer.ts 2.2 KB runs code
- sdk-package/src/bridge-transports/composio-direct.ts 2.5 KB runs code
- sdk-package/src/bridge-transports/runtime-broker.ts 4.9 KB runs code
- sdk-package/src/bridge.ts 3.2 KB runs code
- sdk-package/src/css.d.ts 70 B runs code
- sdk-package/src/holaboss-ui.d.ts 256 B runs code
- sdk-package/src/index.ts 2.6 KB runs code
- sdk-package/src/runtime/action-runner.ts 6.8 KB runs code
- sdk-package/src/runtime/db-view.ts 2.2 KB runs code
- sdk-package/src/runtime/integration-status.ts 5.3 KB runs code
- sdk-package/src/runtime/local-action-api.ts 7.6 KB runs code
- sdk-package/src/runtime/manifest.ts 3.2 KB runs code
- sdk-package/src/runtime/mcp-server.ts 18 KB runs code
- sdk-package/src/runtime/provider-effect-action.ts 7.9 KB runs code
- sdk-package/src/runtime/state-backend-sqlite.ts 12 KB runs code
- sdk-package/src/runtime/state.ts 3.1 KB runs code
- sdk-package/src/runtime/sync-runner.ts 3.3 KB runs code
- sdk-package/src/types.ts 15 KB runs code
- sdk-package/tsconfig.json 540 B
- ui-reference/components.json 596 B
- ui-reference/themes/holaos.css 5.0 KB
- ui-reference/tokens.css 15 KB
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.
- 9d ago First seen · 573 lines · 47 tokens per session scan A a566b1688856
app-builder-sdk is a skill published in the GitHub repository holaboss-ai/holaOS (11,191 stars, last pushed 19d ago), with no licence file. It adds 47 tokens to every session and 10,500 once invoked, about $0.0002 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
oma-architecture
Architecture specialist for software/system design, module and service boundaries, tradeoff analysis, and stakeholder synthesis. Uses context-aware methods such as diagnostic routing, design-twice comparison, ATAM-style risk analysis, CBAM-style prioritization, and ADR-style decision records.
architecture
Greenfield architecture design: map functionality flows, draw components, design APIs, classify dependencies, plan observability. For multi-component, API, schema, auth, or integration-heavy work. For retrofitting existing code, use codebase-hygiene instead.
yao-process
Yao process execution expert. ALWAYS invoke this skill when the user needs to call a Yao process, query data models, run scripts, or check process permissions. Do not call processes without checking this skill first.
oma-backend
Backend specialist for APIs, databases, authentication with clean architecture (Repository/Service/Router pattern). Use for API, endpoint, REST, database, server, migration, and auth work.
agent-operated-software
Use when designing, building, operating, or diagnosing an ongoing application whose live backend or control loop includes OpenRig agents, including applications with a Markdown, YAML, or JSON agent control plane or a thin surface over specialist agent roles.
posthog
Complete guide for the PostHog plugin — REST API access for querying analytics with HogQL, managing feature flags, inspecting events and persons, reading insights, experiments, cohorts, surveys, and more.