Borrowing it
Nothing to install: this file belongs to ai-swiss/base. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/base-contributor/skills/processes/open-change/SKILL.mdgit clone --depth 1 https://github.com/ai-swiss/baseWrote 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/ai-swiss/base/open-change)<a href="https://agentmods.dev/skills/ai-swiss/base/open-change"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/open-change/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.00589 |
| Opus 5.5 | $0.00015 | $0.00236 |
| Sonnet 5.5 | $0.00007 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
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 1mo 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.
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
- 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). - Copy the template. From
decisions/_template.mdtodecisions/YYYY-MM-DD-slug.md(today's date and a short slug). Fill Status, Context, Decision (with the concrete mechanism), Consequences, and the Alternatives table. A decision without alternatives is unproven. - If it is an architecture decision, allocate its
AD-*id withnode tools/spec/new-id.mjs, add the row to theAD-*table inspecs/current/10_core/requirements.md, and link it to the record. - Add the index row to
decisions/index.md(newest first). - Hand off to
implementto build it, and toverifybefore 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.
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.
- 1mo ago Changed 6b85ccc7110f
- 2mo ago First seen · 51 lines · 37 tokens per session scan A aaf2a4ac6bba
open-change is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 37 tokens to every session and 589 once invoked, about $0.0001 per session on Opus 5.5. 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.
open-change compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| open-changeai-swiss/base | Skill | 65 | 8d ago | Apache-2.0 | A | 37 | Claude Code |
| adr-documentationMadAppGang/claude-code | Skill | 287 | 7mo ago | MIT | A | 60 | Claude Code |
| vaultjoelhooks/joelclaw | Skill | 65 | yesterday | none | A | 82 | Claude Code |
| complianceericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 96 | Claude Code, Codex |
| wallet-cliBofAI/skills | Skill | 164 | 4d ago | MIT | A | 92 | Codex |
| actualactual-software/actual-skill | Skill | 6 | 2d ago | Apache-2.0 | A | 157 | Claude Code |
| evidence-anchorsarmanfatemi/nullius | Skill | 5 | 6d ago | MIT | A | 104 | Claude Code |