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.
npx agentmods add commands/higoralves/orc/envgit clone --depth 1 https://github.com/HigorAlves/orcWhat 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 | $0.00034 | $0.01472 |
| Opus 5 | $0.00017 | $0.00736 |
| Sonnet 5 | $0.00007 | $0.00294 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
env 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 2d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orc:env
Give the current project (or workspace) a running dev environment — the same one /orc:qa and /orc:flow boot before browser QA. Standalone uses: "I want to poke at the app", pre-warming the env before a QA run, checking what's up, tearing down.
When NOT to use
Production deploys, remote/cloud environments, Kubernetes — out of scope by design (see orc:docker-best-practices's hand-off list). This command provisions local dev environments only.
Arguments
up(default) — provision or attach. Honors the full detection ladder fromorc:env-provisioning.status— read-only: state file + livedocker compose psverification + orphan sweep.down— tear down the current branch's environment. Destructive; previews and confirms first.--containerize-app— force a full app container when nothing exists (default is hybrid: services in Docker, app on host).--rebuild— force--buildon boot regardless ofbuildInputsHash.--fresh— ignore reusable state:downfirst, then re-provision from scratch.--down-volumes— withdown: also remove named volumes (default keeps them so the next boot reuses DB data).--wait-timeout <s>— healthcheck wait budget (default 120).--repos a,b/--repo a/--all-repos/--this-repo— workspace-mode targeting. Seeorc:workspace-mode.
Workflow
Phase 0 — Detect context
!orc-workspace-detect --banner
Context is injected above (ORC_* vars are exported for any Bash you run — do not re-run detection). loose context → surface and stop (no state dir to write). In workspace mode, resolve target repos from flags or AskUserQuestion — iron rule: no silent broadcast.
Phase 1 — Resolve the verb + state path
$verb is the first argument (up when empty). State file: orc-docker-env state-path "$ORC_STATE_DIR" <sanitized-branch> — in workspace mode the workspace-level state dir; single-repo mode the repo's.
Phase 2 — up
- Invoke the
orc:env-provisioningskill (announce it). Quick attach check first:orc-docker-env is-ready <state-file>—ready→ echo the reuse line (project, services, appUrl, "reused") and skip to step 3. - Dispatch
orc-env-provisionerviaTask. Pass:repoPath(worktree),stateDir,sessionId(sanitized branch perorc:state-protocol), the flags, and — workspace mode —repos[]/repoPaths,webSurfaceRepo(from the plan's "Repo touchpoints" when present), plan path for dependency order. Onfailedverdict: re-print the agent's 🛑 callout andAskUserQuestion— retry /--freshretry / abort. Onfallback: re-print the ⚠️ callout and continue. - Register the session. If
.orc/orc.jsonhas an in-progress session for this branch, appenddocker_env_status: <status> (…)to its checkpoint. Otherwise register a lightweight entry (command: "env",status: "in_progress", branch,startedAt) so/orc:statusshows the running environment and/orc:cleanupcan find it. - Echo: state path, appUrl + serviceEndpoints, boot seconds, reused flag.
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.
- 2d ago First seen · 102 lines · 34 tokens per session scan A b02ec73d446a
env is a command published in the GitHub repository HigorAlves/orc (6 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 1,472 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
launch-sandboxed
Launch an autonomy-loop terminal inside the srt OS sandbox (allow-only writes + an egress allowlist that also bounds the researcher web-fetch).
dockerfile
Validate Dockerfiles for GPU/CUDA configuration issues before building.
deploy
Build, test, deploy with staged rollout.
deploy
Build a container image, push it, and deploy the service to the Akka platform. This is the transition from local development to development on the AAO platform.
t800-onboard
Для чата с новичками. Показывает, что настроено в Cursor (global + local), и что умеет отдел T-800.
triage
Triage review findings one by one — present pending TODOs for user decision (approve, skip, modify).