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 wyattowalsh/agents --skill new-projectgit clone --depth 1 https://github.com/wyattowalsh/agentsWrote 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/wyattowalsh/agents/new-project)<a href="https://agentmods.dev/skills/wyattowalsh/agents/new-project"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/new-project/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/wyattowalsh/agents/new-project"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/new-project.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 | $0.00060 | $0.02574 |
| Opus 5.5 | $0.00024 | $0.01030 |
| Sonnet 5.5 | $0.00012 | $0.00515 |
| Haiku 4.5 | $0.00006 | $0.00257 |
Grade A, and why
new-project 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 1mo 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Project
Plan and safely bootstrap modern software projects from typed presets and capability preferences.
Dispatch
$ARGUMENTS |
Action |
|---|---|
| Empty | Gallery: show modes, presets, preference categories, examples; do not edit |
prefs, prefs list, catalog |
Preferences: list capability categories and defaults |
prefs validate |
Preferences: validate capability and preset catalogs |
prefs add <id> |
Preferences: explain the safe preference addition workflow |
preset list |
Presets: show curated presets and tradeoffs |
plan <name-or-path> |
Plan: read-only blueprint for a new or existing target |
init <name>, new <name> |
Init: new target setup after preflight, blueprint, and approval |
bootstrap <path>, init-existing <path> |
Bootstrap Existing: non-destructive missing-file setup |
audit <path> |
Audit: read-only scaffold and convention health report |
repair <path> |
Repair: approved additive repair based on audit findings |
doctor <path> |
Doctor: validate toolchain/config health without changing files |
docs <path> |
Docs: classify docs-lite, docs-themed, docs-interactive, or docs-product |
docs-lite <path>, starlight <path> |
Docs Lite: Astro Starlight static docs profile |
docs-themed <path> |
Docs Themed: Starlight plus CSS/Tailwind brand layer |
docs-interactive <path> |
Docs Interactive: Starlight plus React islands |
docs-product <path>, fumadocs <path> |
Docs Product: Next.js plus Fumadocs advanced docs profile |
ai <path>, agents <path> |
AI Instructions: AGENTS, nested AGENTS, Claude Code, OpenCode, Codex planning |
github <path> |
GitHub: CI, templates, release workflow planning |
python <name>, uv <name> |
Init/Plan: Python-focused preset |
node <name>, web <name>, next <name> |
Init/Plan: Node/web preset |
data <name> |
Init/Plan: Supabase, SQLite, DuckDB, notebooks preset |
aws <name>, agentcore <name> |
Plan: Bedrock/AgentCore planning; provider mutation is opt-in |
monorepo <name>, nx <name> |
Init/Plan: monorepo preset |
full <name>, max-free <name> |
Plan: comprehensive blueprint; apply module-by-module only |
| Natural language new repo/bootstrap request | Auto-classify, then ask only high-impact missing questions |
| Product feature request | Refuse or redirect to implementation skills |
| Agent or MCP server request | Refuse or redirect to agent-conventions or mcp-creator |
| Destructive or force request | Stop, explain risk, require file-by-file approval |
What ships with it
60 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.
- data/capabilities.json 45 KB
- data/capabilities.schema.json 1.6 KB
- data/command-groups.json 753 B
- data/conflicts.json 570 B
- data/package-aliases.json 492 B
- data/presets.json 8.7 KB
- data/presets.schema.json 801 B
- evals/evals.json 17 KB
- evals/fixtures/cloud-config-present/wrangler.jsonc 35 B
- evals/fixtures/dirty-worktree-repair/README.md 25 B
- evals/fixtures/empty-repo/.gitkeep 0 B
- evals/fixtures/existing-ai-configs/AGENTS.md 246 B
- evals/fixtures/existing-docs-root/docs/README.md 16 B
- evals/fixtures/existing-node-repo/package.json 61 B
- evals/fixtures/existing-python-repo/pyproject.toml 58 B
- evals/fixtures/preferences-present/.new-project-preferences.json 28 B
- references/adding-preferences.md 617 B
- references/ai-agent-instructions.md 530 B
- references/ai-apps.md 599 B
- references/artifact-templates.md 584 B
- references/capability-model.md 1.6 KB
- references/cloud-deploy-dns.md 736 B
- references/conventional-commits-release.md 401 B
- references/data-platforms.md 620 B
- references/design-system.md 555 B
- references/docs-fumadocs.md 551 B
- references/docs-starlight-react.md 942 B
- references/github-ci-release.md 396 B
- references/intake-and-routing.md 1.2 KB
- references/node-pnpm-npm.md 716 B
- references/openspec-governance.md 428 B
- references/precommit-quality-gates.md 485 B
- references/preference-catalog.md 952 B
- references/presets.md 1.1 KB
- references/python-uv.md 829 B
- references/scaffold-profiles.md 955 B
- references/security-supply-chain.md 1.5 KB
- references/validation-and-repair.md 877 B
- references/workflow.md 812 B
- scripts/asset_toolkit/__init__.py 303 B runs code
- scripts/asset_toolkit/_shared.py 5.6 KB runs code
- scripts/asset_toolkit/common.py 3.0 KB runs code
- scripts/asset_toolkit/package.py 43 KB runs code
- scripts/asset_toolkit/validate_evals.py 11 KB runs code
- scripts/asset_toolkit/validate_hooks.py 13 KB runs code
- scripts/asset_toolkit/validate_skill.py 3.6 KB runs code
- scripts/blueprint.py 4.4 KB runs code
- scripts/catalog_utils.py 8.7 KB runs code
- scripts/check.py 3.0 KB runs code
- scripts/doctor.py 1.4 KB runs code
- scripts/openspec_cli.py 3.3 KB runs code
- scripts/preferences.py 4.0 KB runs code
- scripts/preflight.py 3.4 KB runs code
- scripts/render_report.py 1.3 KB runs code
- scripts/validate_catalog.py 4.9 KB runs code
- scripts/validate_plan.py 3.1 KB runs code
- scripts/version_check.py 2.2 KB runs code
- templates/blueprint-dashboard.html 2.0 KB
- templates/preference-matrix.html 1.4 KB
- templates/scaffold-audit.html 1.1 KB
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.
- 1mo ago First seen · 171 lines · 60 tokens per session scan A 7dfa61bb8a83
new-project is a skill published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 2,574 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…