continue

continue is a command for Claude Code from design-and-deliver/claude-code-autoconfig. It costs 22 tokens per session (4,385 once invoked), scanned A, original, MIT.

A command that recovers the previous coding session's last active task and reports its current state.

In plain words
What is it for?
Use it at the start of a resumed terminal session, then approve the reported next step in a new turn.
Why use it?
It saves time when returning to interrupted work by rebuilding the relevant context and identifying the next action.

Command for Claude Code

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 commands/design-and-deliver/claude-code-autoconfig/continue
Clone the repo
git clone --depth 1 https://github.com/design-and-deliver/claude-code-autoconfig

Made for: Claude Code.

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 continue

README.md
[![agentmods](https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/continue.svg)](https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/continue)
Your own site
<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/continue"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/continue.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,385 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 $0.00022 $0.04385
Opus 5 $0.00011 $0.02193
Sonnet 5 $0.00004 $0.00877
Haiku 4.5 $0.00002 $0.00439

Measured 3d ago against content hash 4fad1aa31068, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

continue 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.

.claude/commands/continue.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Continue where the previous session in this terminal left off.

This is the no-ceremony wrapper around /recover-context's auto mode: no arguments, it figures everything out itself, and it is plan-aware (below). Recovery is mechanical re-reading — probe, read, reconcile — so it wants the cheapest model that can do it. What that cheap model must NOT do is the resumed work itself. So this command ends its turn at the report: state recovered, the one next action named, a go-ahead question. The user's next prompt ("go") starts a fresh turn with the recovered context already in the conversation.

End the turn on a plain text question — never an AskUserQuestion picker. A picker answer continues the SAME turn, so the work it green-lights runs inside the recovery turn — exactly what the stop exists to prevent. This overrides any local end-of-turn convention that prefers a picker for closed choices. Ask in text, end the message, wait.

There is no model pin, and v9–v16's claim that there was one was wrong (removed v17). Claude Code ignores command model: frontmatter at runtime — a known bug (anthropics/claude-code#45191, closed "not planned"): the pin parses into command_permissions as claude-sonnet-5, yet every call in the turn runs on the session's main model. Measured 2026-08-23 on 2.1.220 across 138 transcripts in one project: of the 85 sessions that ran /continue, not one switched model at the command boundary — Fable sessions stayed Fable, Opus sessions stayed Opus. So the frontmatter line is gone rather than left in place looking load-bearing. Recovery costs whatever the session's own model costs; to make it cheap, switch the session with /model sonnet BEFORE running /continue (model is per-session, so remember to switch back before the resumed work).

Never verify the model from your own system prompt — it lies on exactly this point. The harness applies the ignored pin to the system prompt TEXT while routing to the real model, so a pinned turn reads as Sonnet in the prompt and bills as Opus in the transcript. That is not theoretical: session 90eb56c6's system prompt said claude-sonnet-5 while all 44 of its requests recorded claude-opus-5, and because v11's check consulted the prompt, it stayed silent through a recovery that cost ~4×. The probe's currentModel field (Step 1) reads the transcript's message.model — the API's own answer — and is the only honest source. /model-probe shares v11's flaw and must not be used for this.

If currentModel is not a Sonnet-class model, append one final line to the report:

⚠ recovery ran on {currentModel} — /model sonnet before /continue to make it cheap.

Nothing else changes — the recovery steps are identical on any model. The line exists so the cost is visible instead of silent.

It is also plan-aware: when the previous session was executing a substep of a phased plan doc (the plan-authoring pattern — a docs/*.md or .claude/plans/*.md with a ## Ledger section) and stayed on that plan through to the end of the session, the plan doc + Ledger is the handoff, not the transcript. If the session moved on to something else afterward, the transcript's tail is the handoff — see Step 3.

Read the full file on GitHub · 281 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. 3d ago First seen · 281 lines · 22 tokens per session scan A 4fad1aa31068

Subscribe to this mod's changes

continue is a command published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 4,385 once invoked, about $0.0001 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.