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 escoffier-labs/skillet --skill reliefgit clone --depth 1 https://github.com/escoffier-labs/skilletWrote 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/escoffier-labs/skillet/relief)<a href="https://agentmods.dev/skills/escoffier-labs/skillet/relief"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/relief/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/escoffier-labs/skillet/relief"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/relief.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 | $0.00076 | $0.01193 |
| Opus 5.5 | $0.00030 | $0.00477 |
| Sonnet 5.5 | $0.00015 | $0.00239 |
| Haiku 4.5 | $0.00008 | $0.00119 |
Grade A, and why
relief 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 7d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
relief
When the shift changes, the outgoing cook leaves the station set and a note on what is simmering; the relief cook reads the note, tastes what is in the pans, and carries on without restarting the stock. This skill is that handover for agent work: a clean stop that a cold-start agent can resume, and a pickup that reads the trail instead of redoing it.
Core principle: the trail says what happened; the artifact says what is true. Trust the first to find your place and the second to decide.
This is not the memory-handoff inbox. A resume note is task state for the next worker and lives in a scratch path. Durable findings (decisions, root causes, gotchas that outlive the task) still go through memory-handoff, never into the resume note alone.
Handing off (pause)
Do this when the user asks you to stop, or when context pressure forces it. "Keep going" is not a request to pause.
- Land the current step. Finish the atomic step you are in or back it out cleanly; begin nothing new. Cancel any helper workers you started and confirm they stopped.
- Change nothing outside the checkout. No push, PR, merge, or outbound message you were not already cleared to send.
- Checkpoint locally. Stage the files you touched by name (never
git add -A) and make onewip:commit. If you are on the default branch, switch to a new local branch first. Do not push it. If the tree is broken, say so in the commit body. Reword or squash it before it joins any PR. - Write the resume note to
"$(git rev-parse --git-common-dir)/relief/<slug>.md"(runmkdir -pon its directory first). That path is inside the repository's git directory, shared by its worktrees and never tracked. Fill in references/resume-note.md: intent, verified progress, state, next step, key files, gotchas. - Tell the user: where you stopped, what is on disk versus only in your head, the checkpoint commit and whether the tree is clean, the note's path, and the first action on resume. This is a pause, not a final report.
What ships with it
3 files 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.
- 7d ago First seen · 55 lines · 76 tokens per session scan A 6f1493245d4e
relief is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 1,193 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-21.
Other skills, from other repositories
handoff
Create a structured session handoff when context is running low or work is pausing. Deep context mining, self-validation, multi-file splitting. Captures everything the next session needs.
context-bankruptcy
Declare bankruptcy on a long-lived AI agent's accumulated memory — audit what it currently believes, separate ground truth from stale and wrong, purge deliberately, restate the truths that survive, and log what was lost. Use when an agent keeps acting on outdated facts, contradicts itself across sessions, 'remembers'…
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so an agent can answer on your team's behalf. Team-scope sibling to second-brain — personal notes go there, not here. Modes — capture, compile (wiki pages + INDEX.md), query (trust-weighted, saved to outputs/)…
second-brain
When you want to capture into, compile, query, lint, or connect your personal Second Brain. Wraps the Karpathy LLM Wiki schema (Obsidian or any markdown vault) — raw/ (unprocessed sources), wiki/ (AI-compiled interlinked topic pages), outputs/ (generated artifacts). Vault defaults to…
claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.
user-profile-keeper
Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes $user-profile-keeper to create, initialize, update, query, correct, delete, export, or audit a local persistent user profile. It can extract durable collaboration…