open-change

open-change is a skill for Claude Code from ai-swiss/base. It costs 37 tokens per session (587 once invoked), scanned A, original, Apache-2.0.

A workflow for recording important engineering decisions in a repository, including the context, chosen approach, and rejected alternatives.

In plain words
What is it for?
It helps document architecture decisions, data or contract changes, and other significant work in indexed, reviewable files.
Why use it?
It keeps the reasoning behind difficult or hard-to-reverse changes available to the team instead of leaving it in personal notes or chat.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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/ai-swiss/base/open-change
Any agent
npx skills add ai-swiss/base --skill open-change
Clone the repo
git clone --depth 1 https://github.com/ai-swiss/base

Made for: Claude Code.

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 open-change

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-swiss/base/open-change.svg)](https://agentmods.dev/skills/ai-swiss/base/open-change)
Your own site
<a href="https://agentmods.dev/skills/ai-swiss/base/open-change"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/open-change.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 587 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 $0.00037 $0.00587
Opus 5 $0.00018 $0.00293
Sonnet 5 $0.00007 $0.00117
Haiku 4.5 $0.00004 $0.00059

Measured 6d ago against content hash aaf2a4ac6bba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

open-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 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.

.ai/agents/base-contributor/skills/processes/open-change/SKILL.md · 51 lines

What it actually says

Open a change

The change plane is decisions/ (tracked, at the repo root), distinct from specs/ (truth) and from the personal scratch of .plans//.reviews/. A record there says what changed and why, with the alternatives that lost. It is lighter than a formal ADR but durable and citable.

Steps

  1. Decide it is worth a record. A carrying or hard-to-reverse choice (a new control, a data or contract shape, a routing/write semantics change) earns one. A trivial change does not; reach for the lightest artifact that preserves the work (the ladder in specs/current/00_overview/les-deux-plans.md).
  2. Copy the template. From decisions/_template.md to decisions/NNNN-slug.md (next free NNNN). Fill Status, Context, Decision (with the concrete mechanism), Consequences, and the Alternatives table. A decision without alternatives is unproven.
  3. If it is an architecture decision, allocate its AD-* id with node tools/spec/new-id.mjs, add the row to the AD-* table in specs/current/10_core/requirements.md, and link it to the record.
  4. Add the index row to decisions/index.md (newest first).
  5. Hand off to implement to build it, and to verify before pushing.

What you never do

  • Edit a closed record to reflect a later change of mind: write a newer record that supersedes it.
  • Put proof in the record: proof is generated into the requirements matrix, never asserted here.
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 · 51 lines · 37 tokens per session scan A aaf2a4ac6bba

Subscribe to this mod's changes

open-change is a skill published in the GitHub repository ai-swiss/base (43 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 587 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

adr-documentation

Architecture Decision Records (ADR) documentation practice. Use when documenting architectural decisions, recording technical trade-offs, creating decision logs, or establishing architectural patterns. Trigger keywords - "ADR", "architecture decision", "decision record", "trade-offs", "architectural decision"…

MadAppGang/claude-code · 60 tokens

ADR Decision Quality

Ensure ADRs capture context, decision, alternatives, tradeoffs, and follow-ups in a way that prevents future drift.

s977043/river-review · 28 tokens

vault

Operate Joel's Obsidian Vault through the joelclaw CLI. Use when reading ADRs/projects, searching notes, listing PARA sections, or auditing ADR hygiene with vault adr commands. Triggers on: 'check the vault', 'read ADR', 'find this note', 'vault search', 'ADR collisions', 'ADR audit', 'decision inventory', or any…

joelhooks/joelclaw · 82 tokens

propose

Draft a Kauri decision for human review before recording it. This skill should be used proactively — when the user makes, confirms, or rejects a non-trivial choice (picking a library, rejecting an approach, choosing an architecture, resolving a trade-off, establishing a convention), invoke this skill to draft a…

mhashim6/kauri · 119 tokens

consult

Consult existing Kauri decisions before planning or implementing changes. Use BEFORE making architectural choices, changing conventions, picking libraries, or modifying files that might be covered by a recorded decision.

mhashim6/kauri · 37 tokens

review

Review recent code changes against Kauri decisions. Use after implementing changes, before committing, during PR review, or when asked "does this look right?" to verify consistency with recorded decisions.

mhashim6/kauri · 39 tokens