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 PetriLahdelma/project-spine --skill project-spine-templategit clone --depth 1 https://github.com/PetriLahdelma/project-spineWrote 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/petrilahdelma/project-spine/project-spine-template)<a href="https://agentmods.dev/skills/petrilahdelma/project-spine/project-spine-template"><img src="https://agentmods.dev/badge/skills/petrilahdelma/project-spine/project-spine-template/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/petrilahdelma/project-spine/project-spine-template"><img src="https://agentmods.dev/badge/skills/petrilahdelma/project-spine/project-spine-template.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 | $0.00066 | $0.00722 |
| Opus 5.5 | $0.00026 | $0.00289 |
| Sonnet 5.5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
project-spine-template 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Template save / apply flow
Goal: reuse a team's agreed-upon project structure (brief scaffold + design rules + compile-time contributions) across client projects.
Template sources, priority order
Project Spine resolves templates from these roots (highest priority first):
- Project-local —
./.project-spine-templates/<name>/committed to the current repo. - User-local —
~/.project-spine/templates/<name>/on this machine. - Bundled —
saas-marketing,app-dashboard,design-system,docs-portal,api-service, andmonorepoship with the CLI.
Same name in a higher tier overrides lower tiers.
Flow A — apply an existing template to a new project
spine template list
Shows all templates reachable from this shell. The [source] column tells the user where each one comes from.
spine init --template <name>
Scaffolds brief.md from the template's starter content. Then follow project-spine-kickoff from Step 3.
Flow B — save the current project as a template
Prerequisite: the user already has a brief.md and ran spine compile at least once. The compiled .project-spine/spine.json is used to derive the template's contributes block automatically.
spine template save \
--name my-agency-saas \
--title "My agency SaaS starter" \
--description "Our marketing site template (Acme Inc.)" \
--location user
--location options:
user(default) — saves to~/.project-spine/templates/<name>/; follows you across projects on this machine.project— saves to./.project-spine-templates/<name>/; commits to the repo, shared via VCS.
When to recommend saving as project-local vs user-local
Save project-local if:
- The template represents a shared agency convention
- Multiple teammates will use it across client projects
- The brief scaffold / design rules include decisions the team has consensus on
Save user-local if:
- It's a personal preference (your favorite starter)
- You're experimenting with a template before committing the team to it
- The team hasn't set up a workspace yet
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 · 74 lines · 66 tokens per session scan A f1633233d4c1
project-spine-template is a skill published in the GitHub repository PetriLahdelma/project-spine (2 stars, last pushed 8d ago), licensed MIT. It adds 66 tokens to every session and 722 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 2026-08-31.
Other skills, from other repositories
ce-compound
Document a recently solved problem or durable project vocabulary in docs/solutions/ or CONCEPTS.md. Use when capturing a learning after work.
ce-work
Execute a plan or concrete work prompt end-to-end. Use when implementing from docs/plans, a spec path, or a clear build request; use ce-debug for open-ended bugs.
loadout-import-workflow
Import another repo's command/skill suite into loadout as a workflow. Use when the user points at an agent framework, plugin, or command pack (e.g. a GitHub repo, a .claude/commands/ directory, a skills pack) and wants its process turned into a loadout [[workflows]] entry — "import this workflow", "turn this plugin…
ce-commit-push-pr
Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.
loadout-migrate
Migrate existing global AI agent instructions into loadout. Use when adopting loadout, importing a CLAUDE.md / AGENTS.md / global agent rules into loadout, setting up /.config/loadout/config.toml, or turning prose agent instructions into reusable fragments and stack-targeted profiles.
loadout-remember
Save a durable, cross-project user preference into loadout's global fragments/profiles — or update the fragment it contradicts. Use when the user states lasting guidance that should follow them across projects and agents ("always X", "never Y", "stop doing Z"), especially when it conflicts with guidance the loadout…