agentmods.dev

spar-init

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.

In plain words
What is it for?
Verifying a spar-kit installation and preparing a repository for the next spar-kit specification step.
Why use it?
It finds stale or incomplete setup and can make safe small repairs or recommendations before further work.

Skill for Claude CodeCodex

17 3mo ago A scan 57 tokens original Apache-2.0
View the source file 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.

agentmods
npx agentmods add skills/jed-tech/spar-kit/spar-init
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.

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. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.01284
Opus 5 $0.00028 $0.00642
Sonnet 5 $0.00011 $0.00257
Haiku 4.5 $0.00006 $0.00128

Measured 3d ago against content hash 0fff0eaa3d65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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:

  1. Version check - compare upstream VERSION to local .spar-kit/VERSION.
  2. Tool verify-install-sync - seed or update .spar-kit/.local/tools.yaml.
  3. AGENTS.md recommendation - encourage a short, effective AGENTS.md for lower token usage and clearer agent behavior.
  4. .gitignore hygiene check - recommend ignoring .spar-kit/.local/ when needed.
  5. 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.

  1. 3d 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 3mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,284 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.

agent-skillsaiai-agentsai-workflowautomationclaude-code
Related

Other skills, from other repositories

clinpgx-database

Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.

foryourhealth111-pixel/Vibe-Skills · 45 tokens

data-quality-frameworks

Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.

foryourhealth111-pixel/Vibe-Skills · 37 tokens

coding-tutor

Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates a persistent learning trail that compounds over time using the power of AI, spaced repetition and quizes.

foryourhealth111-pixel/Vibe-Skills · 44 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

data-artist

Create beautiful data visualizations with mathematical elegance, color theory, and narrative design - the "Data is Beautiful" aesthetic.

foryourhealth111-pixel/Vibe-Skills · 28 tokens

docx-comment-reply

Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.

foryourhealth111-pixel/Vibe-Skills · 39 tokens