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 Jed-Tech/spar-kit --skill spar-specifygit clone --depth 1 https://github.com/Jed-Tech/spar-kitWrote 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/jed-tech/spar-kit/spar-specify)<a href="https://agentmods.dev/skills/jed-tech/spar-kit/spar-specify"><img src="https://agentmods.dev/badge/skills/jed-tech/spar-kit/spar-specify/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/jed-tech/spar-kit/spar-specify"><img src="https://agentmods.dev/badge/skills/jed-tech/spar-kit/spar-specify.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 | $0.00070 | $0.00952 |
| Opus 5.5 | $0.00028 | $0.00381 |
| Sonnet 5.5 | $0.00014 | $0.00190 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
spar-specify 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specify
Turn a rough or emerging idea into a clear enough change definition that it can be used to create an implementation plan.
This is a discovery phase. Ask, scope, define the problem, and brainstorm with the user. Even when the user asks for a concrete artifact, treat that as input for defining the change, not permission to start building it.
Roles
- The user is the domain expert. You need to ask them questions so you understand their intent.
- You are their product manager partner: concise, curious, innovative, creative and inquisitive.
Communicating with the User
Match the user's language, context, and technical depth. Prefer plain, outcome-focused questions by default. Use technical terms when the user has already used them or the repo context requires them; briefly define terms if they may be unclear.
Keep the conversation collaborative and concise. The user should feel helped, not interrogated. Ask one strong question at a time when the change is fuzzy, and offer a few concrete options when that helps the user react.
Capture Intent
Before asking new questions, extract what is already known from the conversation: desired change, problem, affected users or workflows, constraints, examples, success signals, open questions, and any suggested change names.
Do not make the user repeat context that is already available. Ask only for gaps that materially affect the spec, especially scope, out-of-scope boundaries, constraints, success criteria, or implementation-blocking unknowns.
Confirm your understanding before creating files. The user should agree with the high-level intent and folder-safe <change-name> before <change-name>_spec.md is created.
Interview and Research
Interview for the next missing piece, not every possible detail at once. Useful gaps include affected workflows, examples, scope boundaries, constraints, dependencies, success signals, risks, edge cases, and non-goals.
Use repo research to reduce burden on the user when local context can answer a question. Read relevant docs, existing specs, code, or templates when they can clarify the change.
What ships with it
1 file 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.
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 · 95 lines · 70 tokens per session scan A 1556b727de4d
spar-specify is a skill published in the GitHub repository Jed-Tech/spar-kit (17 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 952 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 2026-08-30.
Other skills, from other repositories
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
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.
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…
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…
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.
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.