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/encrypt-helpernpx skills add trustabl/trustabl --skill encrypt-helpergit clone --depth 1 https://github.com/trustabl/trustablWrote 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/trustabl/trustabl/encrypt-helper)<a href="https://agentmods.dev/skills/trustabl/trustabl/encrypt-helper"><img src="https://agentmods.dev/badge/skills/trustabl/trustabl/encrypt-helper.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.00191 |
| Opus 5 | $0.00010 | $0.00096 |
| Sonnet 5 | $0.00004 | $0.00038 |
| Haiku 4.5 | $0.00002 | $0.00019 |
Grade A, and why
encrypt-helper 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 4d 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
Encrypt Helper (synthetic test fixture)
This is a synthetic Trustabl test fixture used to exercise the
skill_name_has_text predicate (CSKILL-080). Its frontmatter name: contains
the "encrypt" marker on purpose. It only reads files the user points it at —
no dynamic-context execution, no external URLs, no bundled scripts, no
prompt-injection markers, no duplicate tool references, and it is not bound
to a specific agent. Its description states a purpose and its body names a
failure path, so it stays silent on CSKILL-085 and CSKILL-083 — CSKILL-080 is
the only skill-scope rule expected to fire.
If a read fails, it stops and reports the failure rather than guessing.
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.
- 4d ago First seen · 19 lines · 21 tokens per session scan A bfff40d47e1c
encrypt-helper is a skill published in the GitHub repository trustabl/trustabl (47 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 191 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.
api-agent-ready
Make ANY API agent-ready without integration code — design/harden the surface with the agent-readiness best-practices checklist (one canonical read, field-complete, clear enums/required fields, machine-authable auth), comprehend its OpenAPI/docs with gecko, emit the agent-native artifacts (llms.txt breadcrumb, x-gecko…