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 agentproto/ts --skill pb-build-appgit clone --depth 1 https://github.com/agentproto/tsWrote 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/agentproto/ts/pb-build-app)<a href="https://agentmods.dev/skills/agentproto/ts/pb-build-app"><img src="https://agentmods.dev/badge/skills/agentproto/ts/pb-build-app/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/agentproto/ts/pb-build-app"><img src="https://agentmods.dev/badge/skills/agentproto/ts/pb-build-app.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 | $0.00058 | $0.00974 |
| Opus 5.5 | $0.00023 | $0.00390 |
| Sonnet 5.5 | $0.00012 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
pb-build-app 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 17d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pb-build-app — package my agents + workflows as an agentproto APP
Goal
Turn a folder of agents and workflows into an installable AIP-53 APP: author it, install it (validation included), apply it to a scope, run its agents, watch the run, tear it down, and share it.
Prerequisites (reference by name): ap-apps, ap-workflows,
ap-spawn-agent (apps spawn agent sessions under the hood), ap-lifecycle.
Steps
1. Author the app directory
Emit with the app-kit builder: defineApp().emit(dir) produces the
canonical layout —
<dir>/
.agentproto/APP.md ← app manifest
agents/AGENT.md ← one per agent
workflows/WORKFLOW.md ← one per workflow
ui/ ← optional UI artifact
Write real content for AGENT.md briefs and WORKFLOW.md stages; the emitted skeleton is not the app.
2. Install — validation is the gate
app_install({ dir: '<ABSOLUTE path to the app dir>' })
Validation checks every WORKFLOW.md tool id against the daemon's
dispatchable tools and reports ALL missing ids AT ONCE (not one at a time).
Fix every reported id and re-install — a successful install returns the
appId. Agent-declared tool refs (e.g. workspace tools like read_file) are
the adapter's own business and are never validated here.
3. Apply to a scope
app_apply({ appId: '<appId>', scopeId: 'root' })
Apply makes the app's capabilities available in that scope. Re-applying the
same app updates the timestamp (idempotent). If the app requires other
apps, apply those to the same scope first.
4. Run the agents
app_run({ appId: '<appId>', sequence: ['scout', 'tailor'] }) // ordered stages
app_run({ appId: '<appId>' }) // concurrent
With sequence, agents run ONE-AT-A-TIME — each waits for its predecessor
to reach a terminal state (bounded ~60x2s) — and all live under the SAME
appRunId. Without sequence, agents spawn concurrently. The mastra-agent
adapter (default) points each spawned session at that agent's emitted
AGENT.md.
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.
- 17d ago Changed 6bf5830461d1
- 1mo ago First seen · 108 lines · 58 tokens per session scan A e1ae571537ce
pb-build-app is a skill published in the GitHub repository agentproto/ts (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 974 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
skill-creator-primer
You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).
llm-wiki
Use when building or maintaining a self-contained personal knowledge base (an LLM wiki) in plain markdown. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki health, auditing article claims against their sources, critiquing a wiki source's reasoning, superseding stale knowledge, 'add to…
extract-wisdom
Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files. Use when asked to extract wisdom or key insights from a given content source.
apply-mantel-styles
Provides guidelines for applying Mantel's brand styles to diagrams and frontend components. Use when asked to create visuals that need to align with Mantel's branding.
home-assistant
This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).