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 valtterimelkko/agent-workflow-skills --skill pi-web-ui-internal-api-orchestrationgit clone --depth 1 https://github.com/valtterimelkko/agent-workflow-skillsWrote 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/valtterimelkko/agent-workflow-skills/pi-web-ui-internal-api-orchestration)<a href="https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/pi-web-ui-internal-api-orchestration"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/pi-web-ui-internal-api-orchestration/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/valtterimelkko/agent-workflow-skills/pi-web-ui-internal-api-orchestration"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/pi-web-ui-internal-api-orchestration.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 | $0.00236 | $0.13950 |
| Opus 5.5 | $0.00094 | $0.05580 |
| Sonnet 5.5 | $0.00047 | $0.02790 |
| Haiku 4.5 | $0.00024 | $0.01395 |
Grade A, and why
pi-web-ui-internal-api-orchestration 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 21d 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.
hand-written curl scripts. **Read `references/pi-orch.md` before your first call**: How it starts
The opening of the file, as written. The whole thing — 842 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pi Web UI Internal API Orchestration
Pi Web UI is a browser interface and backend sitting in front of several agent runtimes. The part that matters here is that it exposes a local-only Internal API over a Unix socket, which turns it into an orchestration control plane you can drive from anywhere on the machine — a different repo, a terminal, a script, a voice assistant — without being inside the web UI at all. Sessions you create land in the same registry the browser uses, so the operator can open them later.
Which job do you want?
The two Pi Web UI jobs split on one question: are you using Pi Web UI, or testing it?
| You are… | Approach | Default target |
|---|---|---|
| Dispatching real agent work — fan-out, comparison, a long task to check back on | this skill | the production socket |
| Proving a change to Pi Web UI or a runtime actually works | the repository's live-validation docs | a disposable server, always |
That distinction decides the safety posture, so get it right before your first
call. Using production here is correct and expected — these sessions are meant
to be visible in the operator's Web UI. What is never acceptable is validating a
code change against production, or stopping, restarting, redeploying, or
reconfiguring the Pi Web UI service on your own initiative — the one exception is a
programme whose owner authorised a restart, run by the parent under the protocol in
references/orchestrator-governance.md. If the task is "does my change work?",
stop and read the live-validation docs.
How to read this skill
This is a reference, not a tutorial — read only what the current job needs, not everything. The usual path: Connect → Golden rule → Choosing the route once, then straight to the numbered step you're on.
This file holds the workflow and the rules that keep you out of trouble. The reference files hold the field-level detail, organised in three reading tiers: must-read on every run, must-read when the situation matches, and optional. Tier 1 is not advisory — skipping it before dispatching is the most common way an orchestration run goes wrong (stale model lists, wrong routes, exhausted provider quota). Tier 2 rows are mandatory within their stated situation and skippable outside it. Tier 3 is genuinely optional.
What ships with it
16 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.
- agents/openai.yaml 401 B
- references/adoption.md 11 KB
- references/antigravity-orchestrator.md 6.3 KB
- references/claude-code-orchestrator.md 7.0 KB
- references/evidence.md 8.1 KB
- references/goals.md 16 KB
- references/multi-phase.md 22 KB
- references/orchestrator-governance.md 17 KB
- references/patterns.md 3.3 KB
- references/pi-orch.md 8.9 KB
- references/programme-kit.md 21 KB
- references/routing.md 5.2 KB
- references/sessions.md 9.7 KB
- references/walk-away.md 23 KB
- scripts/test-wait-watch-restart.sh 2.1 KB runs code
- scripts/wait-watch.sh 3.5 KB runs code
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.
- 21d ago Changed · +17 lines 63c2f5153dd5
- 22d ago Changed · +14 lines 3746b559b542
- 24d ago First seen · 811 lines · 236 tokens per session scan A c6eeb3ab7b47
pi-web-ui-internal-api-orchestration is a skill published in the GitHub repository valtterimelkko/agent-workflow-skills (2 stars, last pushed 21d ago), licensed MIT. It adds 236 tokens to every session and 13,950 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-10-01.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.