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/vunm-io/passdown/passdown-dispatchnpx skills add vunm-io/passdown --skill passdown-dispatchgit clone --depth 1 https://github.com/vunm-io/passdownWhat 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 | $0.00054 | $0.01832 |
| Opus 5 | $0.00027 | $0.00916 |
| Sonnet 5 | $0.00011 | $0.00366 |
| Haiku 4.5 | $0.00005 | $0.00183 |
Grade A, and why
passdown-dispatch 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 3d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Passdown Dispatch
The orchestrator session should stay small and cheap. Route each task to the cheapest executor that can do it well; keep only judgment-heavy work in the main session.
Execution gate
Run this skill before execution begins when any of these conditions apply:
- the plan or change has three or more pending tasks;
- any task has a
[dispatch: ...]tag; - any pending task is independently delegable or mechanical; or
- another installed skill or plugin is about to execute the plan, including
Superpowers
executing-plans.
Do not enter an inline plan executor, Superpowers executing-plans, an
external CLI adapter, or a native subagent executor until routing is complete.
The gate may still route every task to main; the required outcome is an
explicit per-task routing decision before implementation starts.
Materialize the decision: when the plan lives in a file (a markdown plan or an
OpenSpec tasks.md), write the routing decision into that file before
execution starts — add the missing [dispatch: ...] tag to each untagged
task. A decision that lives only in the session transcript is lost at the next
handoff.
A direct user instruction to execute one clearly scoped task does not require
this gate unless that task itself requests delegation. When a user explicitly
asks to bypass delegation and work only in the current session, honor that
choice and route the relevant tasks to main rather than silently skipping the
gate.
Configuration (read first)
Build the effective passdown configuration root-to-nearest. Read applicable
AGENTS.md files from the workspace/repository root down to the current
directory, plus any parent file explicitly referenced by a thin entrypoint.
Merge ## passdown keys in that order: nearer values override the same key and
inherit omitted keys. Resolve relative paths against the file that declared
them.
Read the effective executors entry, cheapest first:
## passdown
- executors: agy, subagent, main # cheapest first; omit what's unavailable
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.
- 3d ago First seen · 146 lines · 54 tokens per session scan A a88b5556a64e
passdown-dispatch is a skill published in the GitHub repository vunm-io/passdown (8 stars, last pushed 14d ago), licensed MIT. It adds 54 tokens to every session and 1,832 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
advogado-criminal
Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.
agent-evaluation-reporting
Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.
agent-orchestration-multi-agent-optimize
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
adhx
Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement metrics. No scraping or browser required.
agent-memory
A hybrid memory system that provides persistent, searchable knowledge management for AI agents.