A setup-check skill for spar-kit, a collection of repository tools. It checks the installed version, local tool settings, AGENTS.md guidance, and whether local files are covered by .gitignore.

Verifying a spar-kit installation and preparing a repository for the next spar-kit specification step.

It finds stale or incomplete setup and can make safe small repairs or recommendations before further work.

spar-init — Skill for Claude Code and Codex by Jed-Tech/spar-kit

Install

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.

Any agent

npx skills add Jed-Tech/spar-kit --skill spar-init

Clone the repo

git clone --depth 1 https://github.com/Jed-Tech/spar-kit

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jed-tech/spar-kit/spar-init/github.svg)](https://agentmods.dev/skills/jed-tech/spar-kit/spar-init)

Your own site

<a href="https://agentmods.dev/skills/jed-tech/spar-kit/spar-init"><img src="https://agentmods.dev/badge/skills/jed-tech/spar-kit/spar-init/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jed-tech/spar-kit/spar-init"><img src="https://agentmods.dev/badge/skills/jed-tech/spar-kit/spar-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,284 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00057	$0.01284
Opus 5.5	$0.00023	$0.00514
Sonnet 5.5	$0.00011	$0.00257
Haiku 4.5	$0.00006	$0.00128

Measured 1mo ago against content hash 0fff0eaa3d65, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spar-init 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.

install-root/skills/spar-init/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Init

Run after spar-kit is installed in a project, or when the user wants a setup check. Treat this as a post-install verification and light repair pass for the repo-local SPAR bundle.

What this skill delivers

Work through these areas in order unless blocked:

Version check - compare upstream VERSION to local .spar-kit/VERSION.
Tool verify-install-sync - seed or update .spar-kit/.local/tools.yaml.
AGENTS.md recommendation - encourage a short, effective AGENTS.md for lower token usage and clearer agent behavior.
.gitignore hygiene check - recommend ignoring .spar-kit/.local/ when needed.
Closeout - a short summary and a recommendation to use spar-specify.

1. Version check

First confirm repository root and note .spar-kit/VERSION.

Canonical: fetch https://raw.githubusercontent.com/Jed-Tech/spar-kit/main/VERSION
Local: <repo>/.spar-kit/VERSION
Compare using SemVer ordering, not string sorting.
If local is missing, invalid, unreadable, or behind upstream: treat the install as stale.
If canonical cannot be fetched: warn that the version check was skipped and continue the rest of init.

When stale:

Do not hand-edit .spar-kit/VERSION.
Recommend rerunning the current install path:
- npx @spar-kit/install
If the user wants help, explain that reinstall is the supported way to refresh the repo-local SPAR bundle.

2. Tool verify-install-sync

Use only .spar-kit/.local/tools.yaml.

Tool state file

Run checks across the full tool set and record missing tools.
If .spar-kit/.local/tools.yaml includes optional recommended tools, check and record their installation status as well.
Batch checks into one command when practical so the user is not prompted separately for each tool.
Continue checking the remaining tools even if one tool is missing or fails.
Capture checked_at in the same batched command when practical so the user is not prompted separately for the timestamp.
Prefer Node for cross-platform UTC timestamp generation: new Date().toISOString().replace(/\.\d{3}Z$/, "Z").
Do not run a second timestamp command if the first timestamp capture succeeds.
If required tools are missing, install them automatically when your permissions allow.
Do not auto-install optional recommended tools unless the user explicitly asks.
Re-check tools that had install attempts, then communicate the final post-install result.
Preserve the existing tools.yaml structure and update entries in place.
For each tool entry, maintain installed, version (when available), and reason (when missing/failing) consistently.
Update checked_at once after the completed full pass.
Respect when rules (for example, uv when the repo uses Python tooling).
Missing optional recommended tools should be recorded with installed: false and a short reason, but should not be reported as blockers.

Read the full file on GitHub · 131 lines

Changes

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 · 131 lines · 57 tokens per session scan A 0fff0eaa3d65

Subscribe to this mod's changes

spar-init is a skill published in the GitHub repository Jed-Tech/spar-kit (17 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,284 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 2026-08-30.

Claude Code agent-skills ai ai-agents ai-workflow automation

similarity-search-patterns

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

foryourhealth111-pixel/Vibe-Skills · 30 tokens

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

foryourhealth111-pixel/Vibe-Skills · 37 tokens

ppt-review

Read this skill before the first deck or output quality review, so its criteria are available when the rendered images arrive. Apply the criteria to current officereview structural output and relevant rendered images. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck…

Orkas-AI/Orkas · 2 tokens

plotly

Interactive scientific and statistical data visualization library for Python. Use when creating charts, plots, or visualizations including scatter plots, line charts, bar charts, heatmaps, 3D plots, geographic maps, statistical distributions, financial charts, and dashboards. Supports both quick visualizations (Plotly…

foryourhealth111-pixel/Vibe-Skills · 85 tokens

material-organizer

Organize only the materials the user has already provided or explicitly pointed to. The job is to make messy inputs easier to scan, reuse, archive, or continue from later while preserving source traceability.

Orkas-AI/Orkas · 3 tokens

seo-crawl

Agent-wide core connector rule: when any connected search console is used, discover its operations with listconnectortools and invoke each selected operation through callconnectortool; naming listsites or an analytics operation without the core invocation is not execution.