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.svg" alt="Measured on agentmods" 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 | $0.01406 |
| Opus 5 | $0.00018 | $0.00703 |
| Sonnet 5 | $0.00007 | $0.00281 |
| Haiku 4.5 | $0.00004 | $0.00141 |
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 6d 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[!WARNING]⚠️ 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.
- 6d ago First seen · 86 lines · 36 tokens per session scan A 03a02d500fe2
resume is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 10d ago), licensed MIT. It adds 36 tokens to every session and 1,406 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.
Other commands, from other repositories
visual
Restate a spec, task, diff, or the current topic as a compact markdown visual digest.
digest
Generate a daily or weekly digest of activity across all connected sources.
cancel-loop
A command for stopping an active automated loop managed through a local Fireauto state file.
configure
An interactive setup command for configuring the Claude HUD, a status display that shows information while you work. It adjusts what appears, along with colors and formatting.
idle-time-setup
Show paste-ready snippet to wire the idle-timing fragment into your existing statusline.
csp-recent
List the user's most recent Claude Code sessions.