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.
npx skills add cz1993/vibe-coding-repository-standard --skill safe-changegit clone --depth 1 https://github.com/cz1993/vibe-coding-repository-standardWrote 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/cz1993/vibe-coding-repository-standard/safe-change)<a href="https://agentmods.dev/skills/cz1993/vibe-coding-repository-standard/safe-change"><img src="https://agentmods.dev/badge/skills/cz1993/vibe-coding-repository-standard/safe-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/cz1993/vibe-coding-repository-standard/safe-change"><img src="https://agentmods.dev/badge/skills/cz1993/vibe-coding-repository-standard/safe-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.00372 |
| Opus 5 | $0.00027 | $0.00186 |
| Sonnet 5 | $0.00011 | $0.00074 |
| Haiku 4.5 | $0.00005 | $0.00037 |
Grade A, and why
safe-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 10d 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
Safe Change
Inputs
- user outcome;
- in-scope behavior/modules;
- explicit non-goals;
- acceptance criteria;
- safety and environment restrictions;
- Git action.
Method
- Trace the current entry point, callers, inputs, outputs, dependencies, and side effects.
- Locate existing code, configuration, tests, and platform facilities before adding anything.
- Define the smallest defensible change and test scenarios.
- Implement only the accepted scope.
- Prefer, in order:
- existing repository behavior;
- language/runtime standard facilities;
- framework/platform features;
- already-installed dependencies;
- direct code;
- a new abstraction or dependency only with current evidence.
- Never simplify away validation, security, privacy, data isolation, error handling, observability, accessibility, migration safety, recovery, or useful tests.
- Add tests at the smallest credible level and cover important boundaries with integration/contract/smoke evidence as applicable.
- Review the complete diff and remove unrelated changes.
- Prepare a test table showing scenario, input/setup, expected, actual, and evidence.
- Use an independent read-only reviewer for non-trivial changes; resolve and recheck blockers.
Output
Report in plain language:
- what changed and why;
- files changed;
- behavior before/after;
- tests and actual outcomes;
- reviewer findings and resolutions;
- unrun validation and residual risk;
- commit/PR identifiers.
Do not expose internal scratchpads or agent transcripts.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 49 lines · 54 tokens per session scan A ca48e631873e
safe-change is a skill published in the GitHub repository cz1993/vibe-coding-repository-standard (21 stars, last pushed 25d ago), licensed Apache-2.0. It adds 54 tokens to every session and 372 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.
Other skills, from other repositories
test-gap-review
Review whether existing tests and verification credibly prove a scoped behavior contract. Use during validation when evidence may omit important behavior or provide false confidence.
crap-index-assess
Assess method-level change risk with the Change Risk Anti-Patterns (CRAP) index and recommend focused testing or complexity reduction. Use when a repository configures CRAP measurement, cyclomatic complexity and automated test coverage data are available, or a user asks what CRAP means, how to calculate or interpret…
behavior-implement
Implement behavior through a red-green-refactor cycle when focused automated tests are proportionate. Use for product behavior changes and for engineering tooling and infrastructure only when native checks are insufficient and concrete complexity or failure risk warrants dedicated tests.
test-design
Design or write reproducible tests matched to behavioral risk before implementation. Use for product behavior and for engineering tooling and infrastructure only when native checks are insufficient and concrete complexity or failure risk warrants proportionate dedicated tests.
phase-validate
Validate exactly one implemented phase or scoped change against its authoritative contract. Use after implementation to re-derive criterion-level conclusions from current evidence and fix only required implementation gaps.
cli-control
Verify terminal-hosted CLI or TUI behavior with repeatable local evidence. Use for output, prompts, interactive input, signals, hangs, resizing, startup, exit status, or terminal restoration.