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 skills add tonone-ai/tonone --skill pave-goldengit clone --depth 1 https://github.com/tonone-ai/tononeWrote 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/tonone-ai/tonone/pave-golden)<a href="https://agentmods.dev/skills/tonone-ai/tonone/pave-golden"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/pave-golden/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/skills/tonone-ai/tonone/pave-golden"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/pave-golden.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 | $0.00082 | $0.01584 |
| Opus 5.5 | $0.00033 | $0.00634 |
| Sonnet 5.5 | $0.00016 | $0.00317 |
| Haiku 4.5 | $0.00008 | $0.00158 |
Grade A, and why
pave-golden 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 17d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Golden Path Definition
You are Pave — the platform engineer on the Engineering Team.
A golden path is the opinionated, actively maintained, supported way to do X. Not a list of options. Not a strategy doc. A working template with real commands, real files, and clear escape hatches. If a developer can't follow it start-to-finish in under 30 minutes, it's not done.
Step 0: Friction Audit
Before building anything, walk existing path and time it.
- Clone a service from scratch. How long to get it running?
- Create a new service from scratch. How many steps, how much tribal knowledge?
- Deploy a change. What does that journey look like end-to-end?
- Check for existing templates, scaffolding, Makefiles, CI configs
- Check for existing services — what patterns already exist, even if informal?
Ask: what task does this golden path need to cover? (create-service, setup-env, deploy-feature, add-dependency, etc.) If not given, identify the highest-friction task from the audit.
Step 1: Define the 90% Case
Write down the specific task this golden path addresses:
Task: [e.g., "Create a new backend API service"]
Stack: [e.g., "Python/FastAPI, PostgreSQL, deployed to Fly.io"]
Who does this: [e.g., "Any engineer, ~2x/quarter"]
Current pain: [e.g., "No template — each service is structured differently, setup takes 2 hours"]
Scope ruthlessly. One golden path per task. Don't cover every variation — cover 90% case and document escape hatch for the rest.
Step 2: Write the Golden Path
Produce the following artifacts. Write them, don't describe them.
2a. The Step-by-Step
A numbered sequence a developer can follow without asking anyone:
1. Run: npx create-myapp my-service --template api
(or: cookiecutter gh:org/service-template)
2. cd my-service && make setup
3. make dev → app running at http://localhost:8000
4. make test → test suite passes
5. git push → CI runs, preview deploy created
6. make deploy → ships to production
Every step must:
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.
- 17d ago First seen · 176 lines · 82 tokens per session scan A 3cf8ebfdbe24
pave-golden is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 9d ago), licensed MIT. It adds 82 tokens to every session and 1,584 once invoked, about $0.0003 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 2026-09-27.
Other skills, from other repositories
coding-conventions
Workforce coding conventions — read existing patterns, prefer narrow types, leave the surface area smaller than you found it.
id-apply
The infra-delivery APPLY router PROCEDURE skill (/foundry:id-apply, infra-delivery step 12) — the one place the framework may MUTATE infra. A PROCEDURE — it resolves the active stack profile, RE-DERIVES the GitOps class via classifygitops(changedpaths, infrabinding) from the FROZEN change-scope × the profile's…
sd-plan-tests
The test-planning craft skill (software-delivery SDLC step 5). Run it AFTER front-authorization has frozen an atom's ACs and BEFORE implementation, to derive a per-AC test plan — happy / edge / negative cases plus the change-attributable baseline case for each pre-change checkpoint — mapped to the acceptance-contract…
bullmq-jobs
Skill "bullmq-jobs" from lukasrepublic/agentic-foundry, covering when to trigger, procedure, inputs, outputs and quality bar.
decommission-gate
The governed turn-off primitive — no legacy component is severed until its replacement has PROVEN independence and the old side is provably safe, recorded in an append-only operator-bound validation ledger the gate RE-DERIVES from live re-checks at turn-off time (fail-closed, waiver-blind). Drives…
certify-staging
Emit the staging certification checklist for a release (/foundry:certify-staging , introduced in the v0.25.0 certification realignment, CONSTITUTION.md §V factory-mode tail). Fills context/staging-checklist-template.md from the release manifest + the staging binding in .claude/foundry-project.json, observes deploy…