resume

A command for continuing an active orchestrated run from its next pending approval point. It can also restart the run from the beginning after confirmation.

In plain words
What is it for?
Use it to resume unfinished lifecycle work or, with --restart, clear the run state and begin again from initialization or ideation.
Why use it?
It avoids repeating completed phases while still allowing a deliberate reset when the run needs to start over.

Command

Part of the guild plugin — 19 skills, 22 commands, 13 agents, 10 hooks, 2 MCP servers shipped together

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/lookatitude/guild/resume
Clone the repo
git clone --depth 1 https://github.com/lookatitude/guild

Or install guild, the plugin that ships this one along with the rest of its 19 skills, 22 commands, 13 agents, 10 hooks, 2 MCP servers.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,376 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 $0.00035 $0.01376
Opus 5 $0.00017 $0.00688
Sonnet 5 $0.00007 $0.00275
Haiku 4.5 $0.00003 $0.00138

Measured 3d ago against content hash 895fed9252b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

commands/resume.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/guild:resume — lifecycle helper

Continues the active run from the next pending gate. No phase — acts on the active run.

--restart replaces the v1 first-word $ARGUMENTS --restart hack.

Args & local flags

  • Args: — (no positional)
  • --no-index — per-invocation filesystem-scan bypass of the optional read-through cache (Invariant FS-CANONICAL: filesystem is always the authoritative source).
  • --restart — clears run state and re-runs from Init/Ideation (confirm-before-clear I).

Gates

Resumes at the next I gate. --restart adds a confirm-before-clear I gate.

Output

Continues the active run's phase artifacts (no new artifact kind introduced).

Run-start preflight (settings-control-and-tmux U3/U6)

resume continues an existing run, so its resolved-settings snapshot is already on disk — run-trace.js start wrote it at the original run-start (since wave 2 the run-trace CLI is the sole caller of runStartPreflight; scripts/lib/runstart-preflight.ts; canonical contract in guild.md §Run-start preflight). Do not re-run the preflight or overwrite the snapshot for the resumed run: read it back with readResolvedSettingsSnapshot(runId, { cwd }).

Re-enter resumable dead lanes (R-016). Before locating the next pending gate, list any resumable dead lanes for the active run: npx tsx ${GUILD_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-$HOME/.local/share/guild/dist/claude-code}}/scripts/resume-lanes.ts <runDir> --json (the --json flag is required for the parseable bare array; without it the CLI prints a human table — scans <runDir>/lanes/*/resume.json, applies the guild.lane_resume.v1 version guard, honors defaults.resume.enabled). For each returned lane, re-enter it via guild:execute-plan's ## Resuming dead lanes (R-016) path — a fresh dispatch from the checkpoint with a fresh retry budget (prior attempts are preserved in the checkpoint for audit, not subtracted). An empty list ⇒ skip straight to the next step (exactly today's behavior). Then proceed to gate continuation.

Read the full file on GitHub · 116 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 · 116 lines · 35 tokens per session scan A 895fed9252b1

Subscribe to this mod's changes

resume is a command published in the GitHub repository lookatitude/guild (7 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 1,376 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.