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/spar-actnpx skills add Jed-Tech/spar-kit --skill spar-actgit 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-act)<a href="https://agentmods.dev/skills/jed-tech/spar-kit/spar-act"><img src="https://agentmods.dev/badge/skills/jed-tech/spar-kit/spar-act.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 | $0.00050 | $0.00989 |
| Opus 5 | $0.00025 | $0.00495 |
| Sonnet 5 | $0.00010 | $0.00198 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
spar-act 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Act
Execute the approved plan.md while preserving the intent and boundaries in
<change-name>_spec.md.
Act is implementation, not replanning. Refine execution details when needed, but do not change product intent, spec constraints, or accepted decisions without user approval.
Inputs
specs/active/<change-name>/<change-name>_spec.mdspecs/active/<change-name>/plan.md- Optional notes or artifacts in the same folder, such as
research.md - Relevant repository code and documentation
If the active spec or plan is missing, stop and use spar-plan first, or
spar-specify if no spec exists.
Execution Context
Before changing files, read the spec and plan together.
- Use spec
Scope,Out of Scope,Constraints,Success Criteria, andDecisionsas fixed implementation anchors. - Use plan
Approachfor the intended technical direction. - Use plan
Execution Constraintsas tactical guardrails. - Execute unchecked
Tasksin order unless reordering is required for correctness. - Use plan
Validation Strategyas the primary validation path. - Track plan
Risks / Follow-upswhile implementing and update them if new information materially changes them.
Execute Tasks
For each unchecked task:
- Understand the task, relevant spec anchors, and affected files.
- Implement the smallest coherent change that satisfies the task.
- Validate using the plan's
Validation Strategy, plus targeted project checks when useful. - Mark the task complete in
plan.mdonly after validation is sufficient.
Keep plan.md accurate as work progresses. It is fine to split, clarify, or
reorder tasks for correctness, but do not alter task intent in a way that changes
the spec.
Research and Blockers
Use repo context first. When errors, APIs, or implementation details are unclear, use available MCP tools, official docs, vendor docs, or web search to understand the issue.
If a task fails:
- Investigate the cause.
- Fix obvious issues and retry once.
- If still blocked, stop, summarize what you tried, explain the blocker, offer concrete next-step options with a recommendation, and ask how to proceed.
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 · 131 lines · 50 tokens per session scan A e33df0d7064b
spar-act is a skill published in the GitHub repository Jed-Tech/spar-kit (17 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 989 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.
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.