change-safety

change-safety is a skill for Claude Code, Codex from storious/agent-playbook. It costs 19 tokens per session (115 once invoked), scanned A, original, MIT.

A method for planning small software changes while protecting existing work and choosing checks that match the risk.

In plain words
What is it for?
Use it to find the code and nearby tests responsible for a change, define the expected behavior, and record the evidence and verification result.
Why use it?
It reduces accidental unrelated edits and prevents a passing test or command from being treated as proof of more than it actually checks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to find the code and nearby tests responsible for a change, define the expected behavior, and record the evidence and verification result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/storious/agent-playbook/change-safety
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.

Any agent
npx skills add storious/agent-playbook --skill change-safety
Clone the repo
git clone --depth 1 https://github.com/storious/agent-playbook

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 change-safety

README.md
[![agentmods](https://agentmods.dev/badge/skills/storious/agent-playbook/change-safety/github.svg)](https://agentmods.dev/skills/storious/agent-playbook/change-safety)
Your own site
<a href="https://agentmods.dev/skills/storious/agent-playbook/change-safety"><img src="https://agentmods.dev/badge/skills/storious/agent-playbook/change-safety/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.

agentmods 80×15 button for change-safety

Your own site · 80×15
<a href="https://agentmods.dev/skills/storious/agent-playbook/change-safety"><img src="https://agentmods.dev/badge/skills/storious/agent-playbook/change-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 115 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00019 $0.00115
Opus 5 $0.00010 $0.00057
Sonnet 5 $0.00004 $0.00023
Haiku 4.5 $0.00002 $0.00012

Measured 9d ago against content hash a8bc3bd60379, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

change-safety 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 9d 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.

.agents/skills/change-safety/SKILL.md · 15 lines

What it actually says

Change Safety

  1. Locate the owning module and its nearest tests before editing.
  2. Describe the intended behavioral change and a verification condition.
  3. Keep unrelated refactors out of the task unless they block correctness.
  4. Treat a passing command as evidence only for what that command actually covers.

Record the relevant evidence, decision, and verification result in the working set or handoff. This skill does not grant tools or bypass host permissions.

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. 9d ago First seen · 15 lines · 19 tokens per session scan A a8bc3bd60379

Subscribe to this mod's changes

change-safety is a skill published in the GitHub repository storious/agent-playbook (2 stars, last pushed 9d ago), licensed MIT. It adds 19 tokens to every session and 115 once invoked, about $0.0001 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 2026-08-31.