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 kyleoliveiro/sg-gov-skills --skill security-testinggit clone --depth 1 https://github.com/kyleoliveiro/sg-gov-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/skills/kyleoliveiro/sg-gov-skills/security-testing)<a href="https://agentmods.dev/skills/kyleoliveiro/sg-gov-skills/security-testing"><img src="https://agentmods.dev/badge/skills/kyleoliveiro/sg-gov-skills/security-testing.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 5.1 | $0.00192 | $0.02888 |
| Opus 5 | $0.00096 | $0.01444 |
| Sonnet 5 | $0.00038 | $0.00578 |
| Haiku 4.5 | $0.00019 | $0.00289 |
Grade A, and why
security-testing 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
security-testing: ST controls for SG government systems
You are setting up or auditing a security testing and vulnerability management programme against the ICT&SS Policy Reform Security Testing family (ST-1..ST-5). The family's scope is the testing lifecycle around a running system: scanning hosts for vulnerabilities, continuously checking cloud configuration, giving the public a way to report what they find, commissioning penetration tests, and remediating what all of those surface within committed timeframes.
The discipline everything hangs on: this family runs on nine agency-defined parameters — scan type and cadence (ST-1), the disclosure channel type (ST-3), the testing type and frequency (ST-4), and four severity-based remediation SLAs (ST-5). The catalog leaves every one of them blank. Get the values from the project's System Security Plan; never invent them. A finding of "scans are too infrequent" is only defensible against the SSP's number.
What this family is not about
ST is the host, cloud, and programme layer. Three things people wrongly park here:
- CI code and dependency scanning is not ST-1. SAST (SD-4), SCA/dependency scanning (SD-5), secret detection (SD-6), and pipeline DAST (SD-9) live in Secure Development (secure-pipeline). ST-1 is host-level vulnerability assessment — the VM, instance, and network layer. A repo with Dependabot and CodeQL has zero ST-1 coverage; don't let "we scan continuously" pass on that basis. The findings from those CI scanners do feed the ST-5 remediation SLAs, though — one register, one clock.
- Container image scanning is CS (container-security), not ST-1.
- Fixing an individual vulnerability is another family's work — a SQL injection fix is AS-1 (secure-coding-as). ST-5 governs the process: triage, priority, the SLA clock, and who may sign a risk acceptance.
Source and currency
Control text in this skill and references/st-controls.md is embedded from
info.standards.tech.gov.sg as of 2026-07-22; the ST family page was last updated 24
March 2026. The standards iterate. For any compliance-critical decision, verify against
the live page:
What ships with it
7 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.
- 8d ago First seen · 190 lines · 192 tokens per session scan A 1892d367c863
security-testing is a skill published in the GitHub repository kyleoliveiro/sg-gov-skills (16 stars, last pushed 1mo ago), licensed MIT. It adds 192 tokens to every session and 2,888 once invoked, about $0.0010 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.