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 EZotoff/ez-omo-config --skill handoff-relaygit clone --depth 1 https://github.com/EZotoff/ez-omo-configWrote 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/ezotoff/ez-omo-config/handoff-relay)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/handoff-relay"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/handoff-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/ezotoff/ez-omo-config/handoff-relay"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/handoff-relay.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 | $0.00066 | $0.00762 |
| Opus 5 | $0.00033 | $0.00381 |
| Sonnet 5 | $0.00013 | $0.00152 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
handoff-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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff Relay — emit and resume
Triggers: /handoff, /handoff emit, /resume-from, "handoff", "new session", "hand this off"
The acceptance boundary (non-negotiable)
- Emit only at stable boundaries: an explicit operator request, a completed work unit, or session close. NEVER emit merely because the context window is filling — a context-pressure snapshot captures an unstable moment and goes stale immediately.
- Resume never auto-continues. The first thing a resuming session does is present the decision checkpoint: continue / revise / archive. Execution begins only after the operator picks.
- The artifact is evidence, not authority.
Emit procedure (/handoff [emit] [slug])
Write .builder-kit/audit/handoff-<slug>-<YYYY-MM-DD>.md (create dirs as needed) with exactly these sections:
# Handoff: <one-line mission>
- emitted: <ISO date-time> | source session: <id> | source head: <commit sha + branch + clean/dirty>
- supersedes: <previous handoff file or "none"> ← update the superseded file's status line if it exists
## Mission
What this thread is for and its current done-condition. 3–6 lines.
## Entry artifacts (read these first)
Numbered files/sections in reading order, each with a one-line "what you'll learn".
## State
- Done (with commit refs)
- In flight (exact coordinates: repo, branch, session IDs)
- Known gotchas / landmines
## Next steps
Numbered, each with a verifiable done-condition.
## Prohibitions
What the receiving session must NOT do (scope locks, "do not touch X").
Rules: cite commits and session IDs, never paraphrase them. If the tree is dirty, say so — a dirty-tree handoff is a warning label, not a blocker. After writing, reply with the file path and nothing else.
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 First seen · 60 lines · 66 tokens per session scan A 75e0309bd17c
handoff-relay is a skill published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 5d ago), licensed MIT. It adds 66 tokens to every session and 762 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 2026-09-06.
Other skills, from other repositories
wiki
LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model).
minimal-code-discipline
YAGNI-ladder coding discipline for writing changes — existence-first, reuse before writing, dependency ladder, shortest correct diff, with non-negotiables that must never be minimized away.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
session-management
Context preservation, tiered summarization, resumability.
context-shunt
Offload large / multi-file reads to a cheap worker model so raw files never enter Claude's context (token savings).
save-progress
Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…