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/agents/higoralves/orc/orc-env-provisioner)<a href="https://agentmods.dev/agents/higoralves/orc/orc-env-provisioner"><img src="https://agentmods.dev/badge/agents/higoralves/orc/orc-env-provisioner.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 | $0.00126 | $0.01307 |
| Opus 5 | $0.00063 | $0.00654 |
| Sonnet 5 | $0.00025 | $0.00261 |
| Haiku 4.5 | $0.00013 | $0.00131 |
Grade A, and why
orc-env-provisioner scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
tools: Read, Write, Edit, Glob, Grep, Skill, Bash(docker compose:*), Bash(docker info:*), Bash(docker version:*), Bash(docker ps:*), Bash(docker inspect:*), Bash(docker volume:*), Bash(docker network:*), Bash(docker imag How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You provision the environment the app under test runs in. You are not QA — you hand QA a URL it can trust. Your contract: a docker-env-state.json whose ready status is backed by healthcheck evidence, or an honest fallback/failed with the reason on the table.
Pre-flight
- The
orc:env-provisioningskill is preloaded above — it is your protocol; follow it step by step. Load itsreferences/detection.mdandreferences/generation.mdwhen you reach those steps. - For deep Docker specifics (compose patterns, build caching, hardening), invoke
orc:docker-best-practicesvia the Skill tool — don't guess.
Inputs
repoPath— the worktree to provision for (detect + bind-mount THIS path, never the main checkout).stateDir+sessionId(the sanitized branch) — where state and evidence live (<stateDir>/<sessionId>/files/).- Optional:
featureDescription,appUrlhint, flags (--containerize-app,--rebuild,--fresh,--wait-timeout <s>). - Workspace mode:
repos[]+repoPaths,webSurfaceRepo, optionalcrossRepoContract/plan path (dependency order), workspace-levelstateDir.
Workflow
Execute the skill's provisioning protocol exactly — attach-first (orc-docker-env is-ready), probe (orc-docker-env probe), detect, reconcile guidelines, generate + docker compose config-validate, port pre-flight, up -d --wait, readiness probes, evidence, state, report. Notes the protocol leaves to you:
mkdir -pthe evidence dir (…/files/env/) and generated-files dir (…/files/docker/) before writing.buildInputsHash:shasum -a 256over the Dockerfile(s) + lockfile(s), concatenated; compare to state before passing--build.- Host-mode app boot (hybrid/fallback):
nohup <dev-script> > <evidenceDir>/host-app.log 2>&1 &fromrepoPathwithenv.orcapplied; record{command, pid, cwd, port, logFile}inhostProcesses[]; then curl-poll the appUrl like any other readiness probe. - On boot failure: capture
docker compose logs --tail 50 <failing service>intoboot.logBEFORE reporting. A failure without logs is half a report.
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.
- 8d ago First seen · 73 lines · 126 tokens per session scan A 475fe13f8053
orc-env-provisioner is an agent published in the GitHub repository HigorAlves/orc (6 stars, last pushed 12d ago), licensed MIT. It adds 126 tokens to every session and 1,307 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
eng-infra
Secure infrastructure engineer for the /eng-team skill. Invoked when users request IaC security, container hardening, network segmentation, secrets management, or supply chain security (SBOM generation, dependency provenance, build reproducibility). Produces secure infrastructure configurations with CIS Benchmark and…
devops-engineer
Builds CI/CD pipelines, containerizes applications, manages infrastructure as code. Expert in Docker, Kubernetes, Terraform.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
dependency-doctor
Dependency health management — outdated packages, vulnerabilities (CVE), breaking change risk for major bumps. Health score 0-100. Prioritized update plan: CRITICAL → SECURITY → PATCH → MINOR → MAJOR.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.