document-change

A documentation workflow for finishing a completed software change. It checks that the specification matches the code, suggests broader documentation updates, and archives the change records.

In plain words
What is it for?
Use it after implementation to update specifications, prepare project-documentation changes for approval, and move completed change files into an archive.
Why use it?
It prevents documentation from describing behavior that the software no longer has. It also preserves decisions and completed change details for later reference.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 624 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 $0.00066 $0.00624
Opus 5 $0.00033 $0.00312
Sonnet 5 $0.00013 $0.00125
Haiku 4.5 $0.00007 $0.00062

Measured 3d ago against content hash b7a881cf419e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

document-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 3d 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.

Research/research/example skills/retain/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document change

Turn completed implementation into clean, accurate, durable knowledge: honest <change-name>_spec.md, captured decisions, broader doc updates only with approval, then archive the change folder.

Inputs

  • Docs/<scope>/Specs/<change-name>/<change-name>_spec.md
  • Docs/<scope>/Specs/<change-name>/plan.md
  • Completed code changes
  • Repository documentation (e.g. README, Docs/technicalBrief.md, setup or usage docs)

Outputs

  • Finalized <change-name>_spec.md (matches actual behavior)
  • Optional updates to broader docs (after approval)
  • Archived folder: Docs/<scope>/Archive/<change-name>/ (contents moved from Specs/)

Workflow

1. Review implementation vs spec

  • Compare implemented behavior with <change-name>_spec.md
  • Note mismatches, missing decisions, outdated assumptions

2. Update <change-name>_spec.md

  • Reflect final behavior (spec must match reality, not original guesses)
  • Update Decisions, Constraints, Success Criteria as needed
  • Resolve or remove stale Open Questions
  • Keep intent-focused; no step-by-step implementation in the spec

3. Identify broader documentation impact

  • Use Documentation Impact in <change-name>_spec.md and the change itself
  • Consider: Docs/technicalBrief.md, README, setup/usage, developer notes

4. Propose broader documentation updates

  • List suggested edits clearly. Be concise.
  • Do not apply until the user approves

5. Apply approved updates

  • Update only what was approved; keep changes minimal and accurate

6. Final cleanup

  • <change-name>_spec.md: clear and complete
  • plan.md: final state (all done or explained); trim noise and temporary notes

7. Archive change

Move the entire folder:

Docs/<scope>/Specs/<change-name>/Docs/<scope>/Archive/<change-name>/

(Create Archive if missing.)

Rules

  • Spec describes final behavior; not a build log
  • No silent edits to README, technical brief, or other repo docs—approval first
  • Stay concise

Read the full file on GitHub · 85 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. 3d ago First seen · 85 lines · 66 tokens per session scan A b7a881cf419e

Subscribe to this mod's changes

document-change is a skill published in the GitHub repository Jed-Tech/spar-kit (17 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 624 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.

Related

Other skills, from other repositories