spar-retain

spar-retain is a skill for Claude Code, Codex from Jed-Tech/spar-kit. It costs 47 tokens per session (917 once invoked), scanned A, original, Apache-2.0.

A closeout process for completed software changes. It reconciles the final implementation with its active specification and plan, then archives the change folder as durable project documentation.

In plain words
What is it for?
Use it after an approved change is complete to update its specification, record what shipped, propose broader documentation updates for approval, and move it from active to completed.
Why use it?
It keeps project records accurate after implementation and preserves the reasons and final behavior without turning the documentation into a noisy activity log.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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-retain
Any agent
npx skills add Jed-Tech/spar-kit --skill spar-retain
Clone the repo
git clone --depth 1 https://github.com/Jed-Tech/spar-kit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for spar-retain

README.md
[![agentmods](https://agentmods.dev/badge/skills/jed-tech/spar-kit/spar-retain.svg)](https://agentmods.dev/skills/jed-tech/spar-kit/spar-retain)
Your own site
<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>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 917 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 5.1 $0.00047 $0.00917
Opus 5 $0.00023 $0.00458
Sonnet 5 $0.00009 $0.00183
Haiku 4.5 $0.00005 $0.00092

Measured 6d ago against content hash 73776d73383c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

install-root/skills/spar-retain/SKILL.md · 117 lines

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.md
  • specs/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, and Out of Scope accurate.
  • Update Constraints if implementation revealed durable requirements.
  • Update Success Criteria so they reflect the outcomes that shipped and were validated.
  • Update Decisions with 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 Tasks are checked or explicitly explained.
  • Ensure Validation Strategy reflects what actually ran or what could not be validated.
  • Ensure Risks / Follow-ups captures unresolved risks, deferred work, or follow-up decisions.
  • Ensure Approach and Execution Constraints do not contradict what shipped.
  • Remove only scratch notes or duplicate lines that would confuse future readers.

Read the full file on GitHub · 117 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. 6d ago First seen · 117 lines · 47 tokens per session scan A 73776d73383c

Subscribe to this mod's changes

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.

Related

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".

KhazP/vibe-coding-prompt-template · 49 tokens

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.

knowns-dev/knowns · 33 tokens

kn-init

Use at the start of a new session to read project docs, understand context, and see current state.

knowns-dev/knowns · 23 tokens

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…

mindfold-ai/Trellis · 65 tokens

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…

mindfold-ai/Trellis · 140 tokens

trellis-channel

Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.

mindfold-ai/Trellis · 32 tokens