relay

relay is a skill for Claude Code, Codex from sonichi/sutando. It costs 57 tokens per session (1,571 once invoked), scanned A, original, MIT.

A handoff note for the next coding-agent session. It records what was in progress, what to check first, possible problems, and important context that automatic session records may miss.

In plain words
What is it for?
Use it when ending a session with unfinished work, a pending code review, an important decision, or a likely failure to investigate next time.
Why use it?
A new session can see facts such as commits and open tasks but may not know the reasoning or the next intended action. The note preserves that continuity.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sonichi/sutando/relay
Any agent
npx skills add sonichi/sutando --skill relay
Clone the repo
git clone --depth 1 https://github.com/sonichi/sutando

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for relay

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonichi/sutando/relay.svg)](https://agentmods.dev/skills/sonichi/sutando/relay)
Your own site
<a href="https://agentmods.dev/skills/sonichi/sutando/relay"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/relay.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.01571
Opus 5 $0.00028 $0.00785
Sonnet 5 $0.00011 $0.00314
Haiku 4.5 $0.00006 $0.00157

Measured 3d ago against content hash fd48ed131c05, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

skills/relay/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Relay

Pass the baton to the next Sutando session. Where session-handoff.sh writes structured facts (recent commits, open PRs, pending Qs), /relay writes the narrative continuity — what you were just working on, what should be checked first, what might break and how to detect it.

Usage: /relay (writes a new relay file) or /relay --append (appends to the most recent unprocessed relay file rather than creating a new one).

Why this exists

src/session-handoff.sh pulls together the structured state for the next session — system status, recent commits, open PRs, pending questions, tasks, conversation tail, quota, repo stats — and writes it to session-state.md. But "I was about to land PR #X and Mini's review said Y matters most" isn't captured by git log, gh pr list, or pending-questions.md tail. The next session reads structured facts but has to RE-INFER the continuity, which costs context and frequently misses the load-bearing decision.

The relay note encodes intent + judgment — the thing only the LLM that lived through the session can write.

Folder layout

Mirrors Sutando's existing tasks/ and results/ convention:

workspace/relay/
├── relay-{epoch_seconds}.md     # pending relay notes (drained into session-state.md, then archived)
└── processed/
    └── relay-{epoch_seconds}.md # already drained; kept for audit
  • File naming: relay-{epoch}.md — sortable + greppable, matches the task-{epoch}.txt shape.
  • Multiple files allowed: /relay always creates a NEW file by default. --append appends to the LATEST unprocessed relay-*.md instead of creating a new one.
  • Consumption: src/session-handoff.sh reads ALL unprocessed relay-*.md files in sorted order, appends them to session-state.md under ## Relay Notes (from prior sessions), then mvs each one to processed/ — but only after confirming its ### <basename> header landed in the written file, so an interrupt cannot retire an uncaptured note.
  • Cleanup: kept indefinitely on local disk. Tiny files (~200-500 bytes each); a year of relay notes is < 1 MB. Sync via the workspace-sync engine (scripts/sync-workspace.sh) for fleet visibility — the legacy sync-memory.sh flow is deprecated in v0.3.0 and removed in v0.4.0.

Read the full file on GitHub · 81 lines

Files

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.

Changes

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.

  1. 3d ago First seen · 81 lines · 57 tokens per session scan A fd48ed131c05

Subscribe to this mod's changes

relay is a skill published in the GitHub repository sonichi/sutando (390 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,571 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 2026-08-30.