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 pandazki/pneuma-skills --skill handoff-pneumagit clone --depth 1 https://github.com/pandazki/pneuma-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/pandazki/pneuma-skills/handoff-pneuma)<a href="https://agentmods.dev/skills/pandazki/pneuma-skills/handoff-pneuma"><img src="https://agentmods.dev/badge/skills/pandazki/pneuma-skills/handoff-pneuma/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/pandazki/pneuma-skills/handoff-pneuma"><img src="https://agentmods.dev/badge/skills/pandazki/pneuma-skills/handoff-pneuma.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 | $0.00117 | $0.03142 |
| Opus 5.5 | $0.00047 | $0.01257 |
| Sonnet 5.5 | $0.00023 | $0.00628 |
| Haiku 4.5 | $0.00012 | $0.00314 |
Grade A, and why
handoff-pneuma 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
enc() { python3 -c 'import sys,urllib.parse;print(urllib.parse.quote(sys.argv[1]))' "$1"; } How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are routing the user's request to Pneuma — a co-creation workspace
that spins up a domain-specific viewer (a deck, a webpage, a board, a
diagram, a video, …) plus an editing agent. Your job in this skill is to
collect the minimum information needed, then call
pneuma handoff-from-external, which mints the session and returns a URL.
The user's request that triggered this skill — whatever they asked you to
hand off or build in Pneuma — is your INTENT. If they invoked you with a
bare $handoff-pneuma and no description, treat INTENT as empty and ask
for it in step 1.
Stop here if you are already inside a Pneuma session
This skill is for external agents (Codex / Claude Code running in the user's normal terminal) that want to hand off TO Pneuma. It is not the path for one Pneuma session to hand off to another.
If the environment variable PNEUMA_SESSION_ID is set (check
echo "${PNEUMA_SESSION_ID:-}"), you are running INSIDE a Pneuma
session. Do not proceed with the steps below — running
pneuma handoff-from-external here spawns a brand-new external session,
leaves your current session alive in "thinking" forever, and confuses the
user with a second window.
Instead, in one short reply tell the user:
I should use Smart Handoff inside Pneuma, not the external handoff-pneuma flow. Trigger Smart Handoff from the UI (or just let me wait for the
<pneuma:request-handoff>tag) and I'll prepare the handoff via$PNEUMA_CLI handoff.
Then end the turn. Do not call any bash commands, do not invoke
pneuma handoff-from-external, do not call pneuma handoff on your own
— the source for <pneuma:request-handoff> is always the user clicking
Smart Handoff in the UI.
Steps
- Resolve
INTENTand any options from the user's request:INTENT— free-form text describing what the user wants built. May be empty.- mode (e.g.
webcraft,slide,diagram) — optional, if the user named one. - project vs. quick — optional. A project initializes the current folder as a Pneuma Project (persistent, multi-session); quick skips project setup (one-off session).
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 Changed · +5 lines 15ca15bb790a
- 1mo ago First seen · 251 lines · 117 tokens per session scan A 02942d31139f
handoff-pneuma is a skill published in the GitHub repository pandazki/pneuma-skills (161 stars, last pushed yesterday), licensed MIT. It adds 117 tokens to every session and 3,142 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
ralph
Launcher for the Ralph-style queue drain script - emits the right node ralph-loop.mjs invocation based on the user's filter and bounds. The actual loop runs as a Node script that opens one server run and spawns one claude -p --worktree per iteration under its own seat; this skill is the configurator, not the loop. Use…
session-retrospective
Analyzes the current implementation run - evaluates schema effectiveness, delegation alignment, note quality, and plan-to-execution fit. Captures cross-session trends and proposes improvements when patterns repeat. Use after implementation runs, or when user says 'retrospective', 'session review', 'what did we learn'…
adopt-project-scope
Migrates an already-populated, unscoped Task Orchestrator database in place to the project-scoping convention — creates a project anchor root, re-parents existing work trees under it, and writes rootId back to config.yaml. Use when a user says: adopt project scope, migrate this database to project scoping, make this…
configure-server
Configures how the MCP Task Orchestrator SERVER runs and is reached — transport (HTTP vs STDIO), the REST API, port publishing, config mounts, and config-sync. Use when a user says: run the server, register the image, set up the Docker container, enable the REST API, set up config-sync, reconfigure the server, change…
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…
quick-start
Interactive onboarding for the MCP Task Orchestrator. Detects empty or populated workspaces and walks through how plan mode, persistent tracking, and the MCP work together. Use when a user says "get started", "how do I use this", "quick start", "first time setup", "onboard me", "what can this MCP do", or "help me…