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 agentmods add skills/jed-tech/spar-kit/specify_and_plannpx skills add Jed-Tech/spar-kit --skill specify_and_plangit 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/specify_and_plan)<a href="https://agentmods.dev/skills/jed-tech/spar-kit/specify_and_plan"><img src="https://agentmods.dev/badge/skills/jed-tech/spar-kit/specify_and_plan.svg" alt="Measured on agentmods" 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 | $0.00121 | $0.01239 |
| Opus 5 | $0.00060 | $0.00620 |
| Sonnet 5 | $0.00024 | $0.00248 |
| Haiku 4.5 | $0.00012 | $0.00124 |
Grade A, and why
plan-change 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 4d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan change
Mandatory first turn
Start by asking — use this wording (or trivially equivalent):
I see you would like to start ideation and planning for a change. Can you provide me with some context or your goals for the change?
If the user already dropped hints in the same thread (e.g. a working title), add at most one short acknowledging clause, then still use the prompt above so goals stay explicit.
Do not create files, do not draft <change-name>_spec.md or plan.md, and do not interrogate for scope, folder name, or success criteria in full — save that for after they reply.
Until scope and change name are confirmed or clearly settled: do not create Docs/<scope>/Specs/<change-name>/ or write <change-name>_spec.md / plan.md. A response that creates files or fabricates spec or Implementation Plan content before that does not follow this skill.
Voice
Be concise, cheerful, and inquisitive — like a helpful teammate, not a form or checklist read aloud.
Convert discussion into durable context and a clear execution plan.
Conversation flow
After the user responds
- Clarify intent and naming (workflow §1): refine
<change-name>as needed through dialogue. - Resolve scope (workflow §2): conversationally confirm
xp_stream|saturation_regen|_Repoif still unclear; only ask what is missing. - Then proceed sequentially through workflow §3 onward (create folder → context → ideate → spec → …). Do not skip ahead (e.g. no
plan.mdbefore<change-name>_spec.mdis stable).
Outputs
Create:
Docs/<scope>/Specs/<change-name>/
<change-name>_spec.md— intent, constraints, decisions (not step-by-step)plan.md(Implementation Plan) — ordered, concrete, verifiable execution steps
Scope must be one of: xp_stream, saturation_regen, _Repo. If unclear, stop and ask.
Workflow
1. Clarify intent and naming
- Understand the goal from discussion; help refine
<change-name>. - Do not create files yet. (See Mandatory first turn and Conversation flow for opener and sequencing.)
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.
- 4d ago First seen · 167 lines · 121 tokens per session scan A acc000c1bc92
plan-change is a skill published in the GitHub repository Jed-Tech/spar-kit (17 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 121 tokens to every session and 1,239 once invoked, about $0.0006 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.
Other skills, from other repositories
vibe-research
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
trellis-session-insight
Reach into past AI conversation history through the trellis mem CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work…
trellis-channel
Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.
kn-research
Use when you need to understand existing code, find patterns, search project knowledge, investigate current external facts, or explore a large codebase before implementation.
trellis-finish-work
Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.