end-resume

end-resume is a skill for Claude Code, Codex from auerbachb/claude-code-config. It costs 89 tokens per session (1,356 once invoked), scanned A, original, MIT.

A resume command for work stopped with /end, restoring selected recoverable tasks while keeping unrelated background work paused.

In plain words
What is it for?
Resuming a stopped session through /go-on, checking what was preserved, and optionally reopening refill activity with the specified option.
Why use it?
It lets an agent continue interrupted work from recorded session state without starting duplicate tasks or reopening background work accidentally.

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/auerbachb/claude-code-config/end-resume
Any agent
npx skills add auerbachb/claude-code-config --skill end-resume
Clone the repo
git clone --depth 1 https://github.com/auerbachb/claude-code-config

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 end-resume

README.md
[![agentmods](https://agentmods.dev/badge/skills/auerbachb/claude-code-config/end-resume.svg)](https://agentmods.dev/skills/auerbachb/claude-code-config/end-resume)
Your own site
<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/end-resume"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/end-resume.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,356 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 $0.00089 $0.01356
Opus 5 $0.00044 $0.00678
Sonnet 5 $0.00018 $0.00271
Haiku 4.5 $0.00009 $0.00136

Measured 4d ago against content hash 36d509292236, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

end-resume 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.

.claude/skills/end-resume/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resume a cost-quiescent /end explicitly. This is the only normal path that reopens the session-scoped launch gate; unrelated messages and timers do not.

/go-on is the primary entry point for resuming. It classifies the stoppage from recorded evidence and routes here when the newest record is an /end, forwarding --resume-refill verbatim — so nobody has to remember which stop happened (Issue #1397; ladder: .claude/reference/universal-resume.md). This command keeps working unchanged and stays the direct path when you already know the session was ended; it remains the executor, and a routed invocation is still an explicit human invocation of it. Portable handoff documents keep naming /end-resume alone in their Resume command: field — that field is lint-restricted to this command because its reader may be outside this harness entirely.

Step 0: Resolve state helpers

Resolve execution-pause.sh, background-task-registry.sh, and session-state.sh using the standard stop-command order: skills worktree, then $HOME/.claude. Do not execute a current-checkout fallback: this command may be invoked from an unrelated or untrusted repository. Parse only --resume-refill.

Before clearing the gate, require all three helpers to be resolved and readable. Use the registry to list the current session and use session-state.sh to read the repo key/refill state. If either inventory is unavailable or malformed, report a degraded resume and leave the execution gate closed. If execution-pause.sh is missing or cannot clear the current ${CLAUDE_SESSION_ID:-default} gate, likewise stop without re-arming anything. A partial resume behind an unknown or unreadable inventory is worse than a visible no-op.

Step 1: Clear the execution gate

Call execution-pause.sh --clear --session "$SESSION_ID". This explicit human invocation authorizes new background starts again. Do not clear the independent .repos[REPO].refill.paused gate unless --resume-refill was supplied.

Read the full file on GitHub · 119 lines

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. 4d ago First seen · 119 lines · 89 tokens per session scan A 36d509292236

Subscribe to this mod's changes

end-resume is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 5d ago), licensed MIT. It adds 89 tokens to every session and 1,356 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 2026-08-31.