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 Miosa-osa/OSA --skill detection-engineeringgit clone --depth 1 https://github.com/Miosa-osa/OSAWrote 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/miosa-osa/osa/detection-engineering)<a href="https://agentmods.dev/skills/miosa-osa/osa/detection-engineering"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/detection-engineering/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/miosa-osa/osa/detection-engineering"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/detection-engineering.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 | $0.00040 | $0.00438 |
| Opus 5.5 | $0.00016 | $0.00175 |
| Sonnet 5.5 | $0.00008 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
detection-engineering 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.
What it actually says
Detection Engineering
Workflow
- Define the behavior, required log source, field mapping, and alert threshold before writing a rule.
- Read
references/workflow.mdfor an original Sigma-format example and controls. Check optionalsigmaCLI availability and installed backend; conversion is not execution. - Replay positive, benign, and missing-field fixtures against the actual chosen backend. Record observed alerts, not just query syntax validity.
- Use
cyber_defenseto exercise embedded lab detection where relevant; never equate its alerts with a real SIEM alert. - Tune exclusions narrowly, rerun all fixtures, and retain rule version plus evidence. Roll back the rule if detection loss or false positives exceed the agreed threshold.
Worked example and prerequisites
Read references/workflow.md before execution. Use only registered OSA tools named in the frontmatter; command examples run through shell_execute. Check command -v for each external executable on the actual target. Optional packages, external collectors and vendor accounts are not bundled or presumed installed.
Evidence and completion
Return scope, prerequisites, exact checks, observed results, evidence paths, limitations, remediation, rollback and retest status. Mark unavailable checks as blocked or unverified. Preserve original evidence and report redacted copies where needed. Work within the authorized environment; do not silently expand to external targets.
Sources
Original OSA workflow and examples. Primary references are linked in the bundled workflow reference, so they remain available when this skill is installed separately. No third-party skill collection or rule pack is vendored.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 39 lines · 40 tokens per session scan A 076a222edd11
detection-engineering is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 11d ago), licensed Apache-2.0. It adds 40 tokens to every session and 438 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
benchmark
Benchmark a local LLM model with MetriLLM. Measures performance (tok/s, TTFT, memory) and quality (reasoning, math, coding, instruction following, structured output, multilingual). Use when the user wants to test, compare, or evaluate a local model.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
skill-authoring
Use when creating new skills, editing existing skills, or verifying skills work before deployment. Applies TDD methodology to skill documentation.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
golang-testing
Go testing best practices including table-driven tests, test helpers, benchmarking, race detection, coverage analysis, and integration testing patterns. Use when writing or improving Go tests.