Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/WaterplanAI/agentic-confignpx agentmods add skills/waterplanai/agentic-config/ac-safety-configure-safetyWrote 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/waterplanai/agentic-config/ac-safety-configure-safety)<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-safety-configure-safety"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-safety-configure-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.
<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-safety-configure-safety"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-safety-configure-safety.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 | $0.00050 | $0.00703 |
| Opus 5 | $0.00025 | $0.00351 |
| Sonnet 5 | $0.00010 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
ac-safety-configure-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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure Safety
Interactive safety.yaml configuration for pi-ac-safety.
Compatibility Note
Use normal chat questions and confirmations for the interactive steps. Do not assume a separate prompt tool.
Trigger
/skill:ac-safety-configure-safety
Behavior
- Read the 3-tier config resolution and display the current effective config:
- Package defaults:
../../assets/config/safety.default.yaml - User-level:
~/.claude/safety.yaml - Project-level:
./safety.yaml(relative to project root)
- Package defaults:
- Display current effective settings per currently shipped guardian:
credential_guardian: blocked paths and allowed filesdestructive_bash: category decisions (deny/ask/allow)write_scope: allowed/blocked prefixes and filessupply_chain: category decisions and allowlistsplaywright: allowed domains, always-blocked/always-allowed tools, and category decisions for blocked-domain navigation, file uploads, and unknown actions on the current Playwright surface
- Ask which guardian(s) to customize.
- For each selected guardian, present the current category decisions and ask for changes:
- Show
category: current_decision - Accept
deny,ask, orallowper category - For list fields, show the current values and ask for additions/removals
- Show
- Ask the target location: project-level (
./safety.yaml) or user-level (~/.claude/safety.yaml). - Generate or update the YAML file at the chosen location.
- Only write overrides; do not duplicate defaults.
- Deep-merge with existing content if the file already exists.
- Validate by loading the merged config and displaying the effective result.
Steps
1. Read ../../assets/config/safety.default.yaml
2. Read ~/.claude/safety.yaml (if it exists)
3. Read ./safety.yaml (if it exists)
4. Display the merged effective config as a table
5. Ask: "Which guardian should be customized? (credential/destructive_bash/write_scope/supply_chain/playwright/all)"
6. For each selected guardian:
a. Show categories with current decisions
b. Ask for a new decision per category (or skip)
c. For list fields, show current values and ask for additions/removals
7. Ask: "Save to project-level or user-level? (project/user)"
8. Write YAML with overrides only
9. Re-read and display the new effective config
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.
- 12d ago First seen · 70 lines · 50 tokens per session scan A 311df16e2781
ac-safety-configure-safety is a skill published in the GitHub repository WaterplanAI/agentic-config (30 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 703 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
vfx-text-cursor
A video or hero-frame effect where a cursor reveals a sentence character by character with coloured trails, light streaks, and a final shimmer.
audit-library-health
Use when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.
install-from-remote-library
Use when installing skills from a shared ai-agent-skills library repo. Inspect with --list first, prefer --collection, and preview with --dry-run before installing.
migrate-skills-between-libraries
Use when moving skills between library workspaces or upgrading from a personal library to a team library. Export from one workspace, import into another.
review-a-skill
Use when evaluating whether a skill belongs in a library. Preview content, check frontmatter, validate structure, and decide whether to keep, curate, or remove.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.