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.
git clone --depth 1 https://github.com/ivuorinen/skillsWrote 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/commands/ivuorinen/skills/prompt-safety)<a href="https://agentmods.dev/commands/ivuorinen/skills/prompt-safety"><img src="https://agentmods.dev/badge/commands/ivuorinen/skills/prompt-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/commands/ivuorinen/skills/prompt-safety"><img src="https://agentmods.dev/badge/commands/ivuorinen/skills/prompt-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 | $0.00000 | $0.03201 |
| Opus 5 | $0.00000 | $0.01600 |
| Sonnet 5 | $0.00000 | $0.00640 |
| Haiku 4.5 | $0.00000 | $0.00320 |
Grade C, and why
prompt-safety scanned grade C with 2 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 7d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
| **direct-prompt-injection** | End-user input concatenated into the prompt with no separation between instructions and data, so a user can override the system prompt ("ignore previous instructions…") | Delimit and label Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
**"The model would never actually output a `rm -rf` / a `DROP TABLE`."** "Would never" is a probability, and the attacker's whole job is to make the improbable output happen. If model output can reach the sink unvalidate Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 7d ago Changed 716f0da12083
- 11d ago First seen · 90 lines · 0 tokens per session scan C 3afe64cd1be9
prompt-safety is a command published in the GitHub repository ivuorinen/skills (3 stars, last pushed today), with no licence file. It costs nothing until one of its globs matches a file; then it loads 3,201 tokens. A static security scan graded it C with 2 findings (instruction-override phrasing, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
exasol
Route any Exasol task through the shared top-level Exasol skill.
openehr-explain
One-stop router that explains or looks up any openEHR thing — auto-detects an archetype, a template, an RM/AM/BASE type, an RM structural concept, an ADL idiom, an AQL query or keyword, or a terminology code (replaces /archetype-explain, /template-explain, /type-spec, /rm-structure, /adl-idiom, /terminology).
log
Show recent git history with summary.
speckit.taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
create-reviewer
Create a new custom reviewer from a natural language description.
history
List past OCR review sessions.