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 SafeAI-Lab-X/ClawKeeper --skill diffsgit clone --depth 1 https://github.com/SafeAI-Lab-X/ClawKeeperWrote 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/safeai-lab-x/clawkeeper/diffs)<a href="https://agentmods.dev/skills/safeai-lab-x/clawkeeper/diffs"><img src="https://agentmods.dev/badge/skills/safeai-lab-x/clawkeeper/diffs/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/safeai-lab-x/clawkeeper/diffs"><img src="https://agentmods.dev/badge/skills/safeai-lab-x/clawkeeper/diffs.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 | $0.00032 | $0.00324 |
| Opus 5.5 | $0.00013 | $0.00130 |
| Sonnet 5.5 | $0.00006 | $0.00065 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
diffs 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 First seen · 23 lines · 32 tokens per session scan A 6fe3e6d74fad
diffs is a skill published in the GitHub repository SafeAI-Lab-X/ClawKeeper (1,018 stars, last pushed 2mo ago), with no licence file. It adds 32 tokens to every session and 324 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.
Other skills, from other repositories
swarmclaw
AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.
halo-cli-operations
Use when operating Halo themes, plugins, attachments, backups, or moments from the terminal. This includes install, upgrade, activate, enable, disable, upload, download, create, delete, reload, and batch maintenance flows. Trigger this skill whenever the user mentions Halo themes, plugins, attachments, backups…
halo-cli-moderation-notifications
Use when moderating Halo comments or replies, creating official replies, managing notifications, listing unread notifications, deleting notifications, or marking notifications as read. Trigger this skill whenever the user mentions Halo comments, comment replies, or notifications in a terminal context.
halo-cli-shared
Use when a task involves Halo CLI, Halo CMS command-line operations, or terminal-based Halo management. Also use when you need shared rules for profiles, JSON output, help discovery, config paths, and destructive actions. Trigger this skill whenever the user mentions 'halo', 'Halo CLI', or terminal operations for Halo…
halo-cli
Use when the task involves Halo CLI, Halo CMS terminal operations, or any command-line interaction with Halo. This includes login, profiles, posts, single pages, search, plugins, themes, attachments, backups, moments, comments, notifications, or shell completion. Trigger this skill whenever the user mentions 'halo'…
halo-cli-search
Use when searching public content on a Halo site with Halo CLI. This includes keyword search, site URL based search, result limits, or any search that does not require authenticated console access. Trigger this skill whenever the user wants to search a Halo site from the terminal, even if they do not explicitly…