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-retainnpx skills add Jed-Tech/spar-kit --skill spar-retaingit 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-retain)<a href="https://agentmods.dev/skills/jed-tech/spar-kit/spar-retain"><img src="https://agentmods.dev/badge/skills/jed-tech/spar-kit/spar-retain.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 5.1 | $0.00047 | $0.00917 |
| Opus 5 | $0.00023 | $0.00458 |
| Sonnet 5 | $0.00009 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
spar-retain 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 6d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retain
Turn completed implementation into durable project knowledge.
Retain is closeout, not a retrospective by default. Make the active spec and plan accurate, preserve useful context, update broader docs only with approval, then archive the whole change folder.
Inputs
specs/active/<change-name>/<change-name>_spec.mdspecs/active/<change-name>/plan.md- Completed implementation in the repository
- Optional notes or artifacts in the same change folder
- Relevant repo documentation, such as README, setup, architecture, or product docs
If implementation appears incomplete, stop and ask whether to return to
spar-act.
Retention Context
Before editing, review the spec, plan, implementation changes, validation results, and optional notes. Preserve optional artifacts unless the user asked to remove them or they are clearly obsolete.
The retained folder should explain what shipped and why it matters without becoming a noisy build log.
Reconcile the Spec
Update <change-name>_spec.md so it describes final behavior and durable intent.
- Keep
Summary,Problem,Scope, andOut of Scopeaccurate. - Update
Constraintsif implementation revealed durable requirements. - Update
Success Criteriaso they reflect the outcomes that shipped and were validated. - Update
Decisionswith important product or technical choices discovered during implementation. - Resolve or remove stale
Open Questions; keep only questions that materially affect future implementation or validation.
Do not add step-by-step implementation narrative to the spec.
Reconcile the Plan
Update plan.md so it remains a useful execution record.
- Ensure
Tasksare checked or explicitly explained. - Ensure
Validation Strategyreflects what actually ran or what could not be validated. - Ensure
Risks / Follow-upscaptures unresolved risks, deferred work, or follow-up decisions. - Ensure
ApproachandExecution Constraintsdo not contradict what shipped. - Remove only scratch notes or duplicate lines that would confuse future readers.
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.
- 6d ago First seen · 117 lines · 47 tokens per session scan A 73776d73383c
spar-retain is a skill published in the GitHub repository Jed-Tech/spar-kit (17 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 917 once invoked, about $0.0002 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".
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.
kn-init
Use at the start of a new session to read project docs, understand context, and see current state.
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.