Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jtsternberg/claude-plugins/plugin install agentmailWrote 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/jtsternberg/claude-plugins/relay-work-order)<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/relay-work-order"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/relay-work-order.svg" alt="Measured on agentmods" 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 | $0.00116 | $0.01825 |
| Opus 5 | $0.00058 | $0.00912 |
| Sonnet 5 | $0.00023 | $0.00365 |
| Haiku 4.5 | $0.00012 | $0.00183 |
Grade A, and why
relay-work-order 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 8d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Relay a work order to another agent
Two agents that share a human need a way to hand work across without a person retyping it.
This is that channel, and it has a protocol — negotiated on this inbox with JT's ChatGPT
agent, which implements the other half as its collaborate-with-claude-via-agent-email
skill.
Read the protocol first
Codex: substitute the installed plugin directory for the path below.
${CLAUDE_PLUGIN_ROOT}/references/agent-mail-protocol.md
That file is the contract: the four subject tags, the four-line body, the threading rules, and the guardrails. Read it before writing or acting on an agent message — the other agent implements the same thing, so a deviation on this side reads as a malformed message on theirs, not as a variation.
Send mechanics — reply vs. reply-all, drafts, threading, the never-retry rule — are in:
Codex: substitute the installed plugin directory for the path below.
${CLAUDE_PLUGIN_ROOT}/references/replying.md
The shape, in one screen
Subject: [HANDOFF] short imperative summary
[ASK] — you want information or analysis back
[FYI] — context only, nothing owed
[DONE] — closing a loop on a prior thread
Goal: one sentence — the outcome the human actually wants
Context: the why, what has been tried, relevant background
Needed: the specific thing you want from the other agent
Refs: repo, file paths, URLs, issue ids — anything it can jump to
[FYI] and [DONE] skip the template. [HANDOFF] and [ASK] do not.
Sending one
Resolve the recipient from the address book, not from memory.
# Codex: substitute the installed plugin directory for this path.
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT}"
bash "$PLUGIN_ROOT/scripts/agentmail-contacts.sh" get "<agent name>"
Repeat that assignment in every block — Codex shells keep no state between blocks. Exit 3
means the agent is not on file. Say so instead of guessing an address: an agent inbox that
looks plausible and is wrong fails silently, because nobody is reading it. Check
verified_from too — an address recorded from conversation rather than from an observed
message is a guess with a filename.
What ships with it
1 file 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.
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.
- 8d ago First seen · 151 lines · 116 tokens per session scan A 1243bbcbeca2
relay-work-order is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed 4d ago), licensed MIT. It adds 116 tokens to every session and 1,825 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…