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 digital-stoic-org/agent-skills --skill relaygit clone --depth 1 https://github.com/digital-stoic-org/agent-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/digital-stoic-org/agent-skills/relay)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/relay"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/relay/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/digital-stoic-org/agent-skills/relay"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/relay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.01573 |
| Opus 5 | $0.00036 | $0.00787 |
| Sonnet 5 | $0.00014 | $0.00315 |
| Haiku 4.5 | $0.00007 | $0.00157 |
Grade A, and why
relay 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 4d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Relay
RELAY is entered at roughly 70% context: one packet to the fresh agent taking over, then you leave. That packet is the whole permitted emission — no preamble to the human, no announcement to peers, nothing after it.
Read nothing, re-run nothing. The skeleton below is complete. You are the agent with the least context left in this fleet, and every token spent re-reading the contract or re-proving a fact you already established is a token missing from the packet itself. ../../references/protocol.md holds the reasoning, for whoever amends the contract. The packet below is what your successor actually inherits — assume it will read nothing else.
1. Gate — are you allowed to relay right now?
In the middle of a cross-item step — a synthesis, a deduplication, a global arbitration, anything reasoning across all the units at once — do not relay. Splitting one makes the result wrong silently and nothing downstream catches it. Finish it, or stop and REPORT, then relay. A saturated agent is exactly the one most tempted to hand off mid-thought: treat that temptation as the cue to run this check, not to skip it.
2. Fill
One line per item, and no prose. A pointer — a path, a path:line, a command — replaces every sentence that would explain it. The only field that carries a why is discarded; everywhere else a justification is the reasoning you already did, retyped at the price of the context this skill exists to save.
role: the scope this name designates
orchestrator: carried over — the successor's only machine recipient
owned_paths: [ABSOLUTE paths; trailing / = whole subtree — outside them you read, you do not write]
hands_off: [shared, high-blast-radius files — a reminder on top of that rule, never the boundary]
read_first: [carried over — the closed list. Anything else, the successor asks the human]
deliverable: ABSOLUTE path carried over — where the work already written lives
established: each fact with the command that proves it, or the path where it is written
discarded: what I tried and rejected, WITH the reason
in_progress: what is half-done, and where it stands
open: what has not been touched
gates: what the human has already decided — do not reopen
what_i_do_not_know: ...
next_action: none — wait for the human
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.
- 4d ago Changed · +21 lines c74779c374d5
- 8d ago First seen · 50 lines · 71 tokens per session scan A 4e1521d4ebc5
relay is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 6d ago), licensed MIT. It adds 71 tokens to every session and 1,573 once invoked, about $0.0004 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 2026-09-04.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…