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 nauta-ai/holster --skill repo-preflightgit clone --depth 1 https://github.com/nauta-ai/holsterWrote 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/nauta-ai/holster/repo-preflight)<a href="https://agentmods.dev/skills/nauta-ai/holster/repo-preflight"><img src="https://agentmods.dev/badge/skills/nauta-ai/holster/repo-preflight/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/nauta-ai/holster/repo-preflight"><img src="https://agentmods.dev/badge/skills/nauta-ai/holster/repo-preflight.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 | $0.00345 |
| Opus 5 | $0.00027 | $0.00172 |
| Sonnet 5 | $0.00011 | $0.00069 |
| Haiku 4.5 | $0.00005 | $0.00034 |
Grade C, and why
repo-preflight scanned grade C with 1 finding 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- credential files (`.env`, `*.pem`, `.aws/credentials`, …) **not** covered by `.gitignore`. What it actually says
Before the user hands this repository (or an MCP config) to an AI agent, commits it, or shares it with anyone, run a Holster preflight and report back.
- Call the
holster.guardtool with the absolute path to the repo. It returns a RUN verdict (safe to run an agent on this locally?) and a SHARE verdict (safe to commit/share this?), plus a ranked fix order. - If either verdict is RISKY, stop and surface the findings plainly before the user proceeds — especially:
- live API keys / secrets sitting in source,
- MCP servers configured to run unpinned code (e.g.
npx/uvxwith no pinned version) or that inherit the full shell environment, - credential files (
.env,*.pem,.aws/credentials, …) not covered by.gitignore. Then walk the user through the fix order, top item first.
- For a deeper pass:
holster.scan_repo(secret scan),holster.check_gitignore(gitignore audit),holster.rotation_playbook(provider-specific rotation steps).
Holster runs entirely locally — the repo never leaves the machine. Never print raw secret values; refer to findings by type and location (file:line) only.
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 · 16 lines · 54 tokens per session scan C fb13e4cca910
repo-preflight is a skill published in the GitHub repository nauta-ai/holster (0 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 345 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
vfx-text-cursor
Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.
pad
Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.
onboard
Link this project to a Pad workspace and set it up.
capture
Capture a thought as a Pad item without breaking flow.
connect
Connect this session to Pad's push/watch stream — consent to receive pushes, and run the workspace's on-session-start ritual on first connect.
status
Project status at a glance — dashboard, active plans, attention items.