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 agentmods add skills/trustabl/trustabl/safe-readernpx skills add trustabl/trustabl --skill safe-readergit clone --depth 1 https://github.com/trustabl/trustablWhat 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 | $0.00026 | $0.00079 |
| Opus 5 | $0.00013 | $0.00039 |
| Sonnet 5 | $0.00005 | $0.00016 |
| Haiku 4.5 | $0.00003 | $0.00008 |
Grade A, and why
safe-reader 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 yesterday.
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 Reader
Read the file the user names and summarize it in three bullet points. Do not modify anything, run commands, or access the network.
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.
- yesterday First seen · 12 lines · 26 tokens per session scan A b65671d2d678
safe-reader is a skill published in the GitHub repository trustabl/trustabl (42 stars, last pushed 5d ago), licensed Apache-2.0. It adds 26 tokens to every session and 79 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 2026-08-30.
Other skills, from other repositories
payload-101
Demonstrate basic injection payloads for training.
format
Run black + isort over a Python file.
lesson-advanced
Advanced red-team lesson on irreversible actions.
lesson1
Privilege escalation lesson.
fetch-installer
Download and install the latest CLI tool.
installing-caplets
Use when a user wants to install, set up, bootstrap, configure, wire, or troubleshoot Caplets for an agent, MCP client, Pi, OpenCode, Codex, Claude Code, self-hosted remote runtime, or local daemon-first setup.