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.
git clone --depth 1 https://github.com/HigorAlves/orcWrote 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/commands/higoralves/orc/resume)<a href="https://agentmods.dev/commands/higoralves/orc/resume"><img src="https://agentmods.dev/badge/commands/higoralves/orc/resume/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/commands/higoralves/orc/resume"><img src="https://agentmods.dev/badge/commands/higoralves/orc/resume.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 | $0.00036 | $0.01401 |
| Opus 5.5 | $0.00014 | $0.00560 |
| Sonnet 5.5 | $0.00007 | $0.00280 |
| Haiku 4.5 | $0.00004 | $0.00140 |
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 20d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:resume
Pick up where an earlier orc command left off. Required for any work that pauses overnight, gets interrupted by another priority, or crashes mid-pipeline.
Arguments
<session-id-or-branch>— optional. If provided, resume that session directly. Accepts either thesessionIdfrom.orc/orc.json(list viaorc-state sessions) or a branch name (sanitized or not); schema perorc:state-protocol.--phase <n>— optional. Skip to a specific phase rather than the next pending one. Use sparingly.--repo <name>— workspace mode only. Drill into a specific repo's slice of a workspace session (e.g.--repo apiresumes only the api side of a cross-repo flow). Phase A scope: this command resumes one repo at a time; broadcast resume across all repos arrives in Phase C.
Workflow
Phase 1 — Detect context + locate the registry
The context banner is injected below (ORC_* vars are exported for any Bash you run — do not re-run detection):
!orc-workspace-detect --banner
Pick the registry to read from the banner's context:
repo— the registry is$ORC_STATE_DIR/orc.json(<repoRoot>/.orc/orc.json). Standard single-repo behavior.repoand<repoRoot>/.orc/<branch>/workspace-link.jsonexists — this repo is a workspace member. ReadworkspaceRootfrom the link file, resolve it against$ORC_REPO_ROOT, and use<workspaceRoot>/.orc/orc.jsonas the registry. Filter sessions to those withreposcontaining this repo's name.workspace— the registry is$ORC_STATE_DIR/orc.json(<workspaceRoot>/.orc/orc.json). Workspace sessions havescope: "workspace"and areposarray.loose— surface a ⚠️ Caution callout (Cwd is neither a git repo nor a workspace parent — nothing to resume.) and stop.
If the chosen registry is missing or has no in_progress sessions, tell the user and stop.
Phase 2 — Choose a session (if not specified)
If a session ID/branch wasn't passed: orc-state sessions --status in_progress renders one line per session — show the list via AskUserQuestion. If only one is active, skip the picker and use it.
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.
- 20d ago Changed 2186b0cffc3b
- 1mo ago First seen · 86 lines · 36 tokens per session scan A 03a02d500fe2
resume is a command published in the GitHub repository HigorAlves/orc (7 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 1,401 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
scout-work
Interactive work session — walks through today's actionable items one at a time, presents a recommended action with draft content, and executes each one only with explicit approval. Runs in the current conversation (not as a background session).
ccc-status
Turn periodic progress updates for long sessions on or off, choose the channel (Slack, Discord, email or console), interval and detail level, or send one now. Use when the user asks to be kept posted, pinged on progress, or to stop updates.
ccc-teleport
Move work between devices: pull a Claude Code on the web session into this terminal with teleport, or keep a local session controllable from the web or mobile app with Remote Control. Use when switching device, monitoring a long task from a phone, or resuming a cloud session locally.
ccc-cloudcli
Open, inspect or start CloudCLI web sessions so Claude Code is reachable from a browser or phone. Use when the user asks for web or mobile access to a running session.