resume-session

resume-session is a skill for Claude Code, Codex from nirecom/agents. It costs 31 tokens per session (511 once invoked), scanned A, original, MIT.

A skill that detects an interrupted interactive workflow and offers to resume the skill that was running. An interactive session is one where the user can answer prompts.

In plain words
What is it for?
Use it to detect paused workflow steps or pending worktree cleanup and choose whether to resume them.
Why use it?
It helps continue unfinished work after a session stops midway instead of starting the workflow over.

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/nirecom/agents/resume-session
Any agent
npx skills add nirecom/agents --skill resume-session
Clone the repo
git clone --depth 1 https://github.com/nirecom/agents

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 resume-session

README.md
[![agentmods](https://agentmods.dev/badge/skills/nirecom/agents/resume-session.svg)](https://agentmods.dev/skills/nirecom/agents/resume-session)
Your own site
<a href="https://agentmods.dev/skills/nirecom/agents/resume-session"><img src="https://agentmods.dev/badge/skills/nirecom/agents/resume-session.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 511 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 $0.00031 $0.00511
Opus 5 $0.00015 $0.00255
Sonnet 5 $0.00006 $0.00102
Haiku 4.5 $0.00003 $0.00051

Measured 3d ago against content hash 7b467590ba0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

resume-session 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/resume-session/SKILL.md · 48 lines

What it actually says

IMPORTANT: Interactive session required. Hard-fail in non-interactive contexts (claude -p, /loop, subagents). Step 1 performs this check before any detection runs.

Purpose

Detects a workflow-state in_progress step or a worktree-end cleanup marker, then dispatches to the matching skill. Session id is read via CLAUDE_ENV_FILE — never CLAUDE_SESSION_ID directly.

Procedure

Step 1 — Hard-fail check

Call AskUserQuestion: "Confirm: resume interrupted workflow session?" with options Resume / Cancel.

  • If AskUserQuestion is unavailable (non-interactive context), abort immediately: output Error: /resume-session requires an interactive session. and stop.
  • If user picks Cancel, stop.

Step 2 — Detect

Run via Bash:

node "$AGENTS_CONFIG_DIR/bin/resume-session-detect"

Parse stdout as JSON. Dispatch by type in Step 3.

Step 3 — Dispatch by type

type Action
none Output "No interrupted workflow detected." and stop.
skill AskUserQuestion "Workflow paused at <step>. Re-run /<skill>?" (Resume / Cancel). On Resume: invoke <skill> skill.
sentinel-wait (step ≠ user_verification) Display hint. AskUserQuestion: Acknowledged (I'll handle manually) / Cancel. No auto-emit, no auto-skip.
sentinel-wait (step = user_verification) Display: "user_verification pending. Emit <<WORKFLOW_USER_VERIFIED: {reason}>> manually when ready." AskUserQuestion: Acknowledged / Cancel. Never auto-emit or auto-advance.

Step 4 — Completion

This skill is an out-of-band utility — emit no workflow step sentinels.

Rules

  • Read workflow state only; never write it.
  • Re-invoked skill idempotency is the called skill's responsibility.
  • /boost is removed (PR #468).
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 · 48 lines · 31 tokens per session scan A 7b467590ba0e

Subscribe to this mod's changes

resume-session is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 511 once invoked, about $0.0002 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.