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 skills/c9r-io/orchestrator/project-bootstrapnpx skills add c9r-io/orchestrator --skill project-bootstrapgit clone --depth 1 https://github.com/c9r-io/orchestratorWrote 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/skills/c9r-io/orchestrator/project-bootstrap)<a href="https://agentmods.dev/skills/c9r-io/orchestrator/project-bootstrap"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/project-bootstrap.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 | $0.00053 | $0.01097 |
| Opus 5 | $0.00026 | $0.00549 |
| Sonnet 5 | $0.00011 | $0.00219 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
project-bootstrap 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Bootstrap
Create a ready-to-run project skeleton with core, portal, docker, and k8s resources.
Quick Start
- Choose a project name and target directory.
- Run the initializer script.
.claude/skills/project-bootstrap/scripts/init_project.py \
--name acme \
--root /path/to/acme
If --name is omitted, the script will prompt (interactive) and default to the target directory name.
By default the initializer supports a safe merge into a non-empty directory (for example a repo root that already contains README.md). It refuses to overwrite existing files and will error if any template top-level paths already exist (for example core/, portal/, .github/).
.claude/skills/project-bootstrap/scripts/init_project.py \
--name acme \
--root /path/to/existing-repo \
If you want strict behavior, require an empty target directory:
.claude/skills/project-bootstrap/scripts/init_project.py \
--name acme \
--root /path/to/acme \
--require-empty
Optional overrides:
.claude/skills/project-bootstrap/scripts/init_project.py \
--name acme \
--root /path/to/acme \
--core-port 8080 \
--portal-port 3000 \
--namespace acme
If host ports conflict with other local stacks, override the Docker Compose bindings at runtime:
CORE_HOST_PORT=18080PORTAL_HOST_PORT=13000
Workflow
- Confirm
--rootand ask the user for a project--name(used for naming, default namespace, and image identifiers). If the user has no preference, suggest a default based on the target directory name. - Run the initializer script with the confirmed parameters.
- Verify local run instructions:
- Core:
cd core && cargo run - Portal:
cd portal && npm install && npm run dev - Docker:
cd docker && docker-compose up -d
- Core:
- Run
project-readinessagainst the generated repo to validate local compose startup, basic tests, and k8s/gh sanity checks. - Hand off the generated skeleton and next steps.
Suggested Dev Loop (After Bootstrap)
What ships with it
28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 175 B
- assets/template/.github/workflows/cd.yml 2.5 KB
- assets/template/.github/workflows/ci.yml 2.5 KB
- assets/template/core/Cargo.toml 275 B
- assets/template/core/Makefile 181 B
- assets/template/core/src/main.rs 2.1 KB
- assets/template/deploy/cleanup.sh 1.4 KB runs code
- assets/template/deploy/deploy.sh 891 B runs code
- assets/template/deploy/upgrade.sh 1.4 KB runs code
- assets/template/docker/docker-compose.yml 397 B
- assets/template/docker/Dockerfile.core 259 B
- assets/template/docker/Dockerfile.portal 168 B
- assets/template/k8s/base/core-deployment.yaml 632 B
- assets/template/k8s/base/core-service.yaml 229 B
- assets/template/k8s/base/kustomization.yaml 109 B
- assets/template/k8s/base/portal-deployment.yaml 415 B
- assets/template/k8s/base/portal-service.yaml 211 B
- assets/template/portal/index.html 310 B
- assets/template/portal/package.json 754 B
- assets/template/portal/src/main.tsx 410 B
- assets/template/portal/src/routes/App.test.tsx 343 B
- assets/template/portal/src/routes/App.tsx 199 B
- assets/template/portal/src/test/setup.ts 44 B runs code
- assets/template/portal/tsconfig.json 255 B
- assets/template/portal/vite.config.ts 267 B runs code
- assets/template/scripts/reset-docker.sh 3.4 KB runs code
- references/stack.md 258 B
- scripts/init_project.py 5.7 KB runs code
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 · 117 lines · 53 tokens per session scan A ebbda413aa8b
project-bootstrap is a skill published in the GitHub repository c9r-io/orchestrator (21 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 1,097 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
rust-check
Run cargo check on the current Rust project to find compile errors.
thread-outbox-provider-push
Publish a fixture thread outbox entry through the Rust thread-outbox-provider front.
neva
Build, review and debug MCP (Model Context Protocol) servers and clients in Rust with the neva crate — tools, prompts, resources, elicitation and multi round-trip requests, Streamable HTTP and stdio transports, auth, DI and deployment. Use whenever Rust code imports neva, whenever the task is to expose something as an…
Rust Standards
Complete Rust coding, linting, testing, architecture, and layer boundary standards for systemprompt.io development.
agentic-infrastructure-2026
Build and adopt production AI agent infrastructure in 2026. Covers framework selection (LangGraph, CrewAI, AutoGen, MCP), orchestration patterns, evaluation, observability, memory systems, and tool use. Also covers the SOCIAL dimension: how to sell agent infrastructure internally, change management, measuring ROI…
azure-keyvault-certificates-rust
Azure Key Vault Certificates SDK for Rust. Use for creating, importing, and managing certificates.