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 sg-gov-secure-coding-asgit 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/sg-gov-secure-coding-as)<a href="https://agentmods.dev/skills/kyleoliveiro/sg-gov-skills/sg-gov-secure-coding-as"><img src="https://agentmods.dev/badge/skills/kyleoliveiro/sg-gov-skills/sg-gov-secure-coding-as/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/kyleoliveiro/sg-gov-skills/sg-gov-secure-coding-as"><img src="https://agentmods.dev/badge/skills/kyleoliveiro/sg-gov-skills/sg-gov-secure-coding-as.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 | $0.00156 | $0.04591 |
| Opus 5.5 | $0.00062 | $0.01836 |
| Sonnet 5.5 | $0.00031 | $0.00918 |
| Haiku 4.5 | $0.00016 | $0.00459 |
Grade A, and why
sg-gov-secure-coding-as scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- For OS commands, use exec-style APIs with argument arrays (`execFile`, `subprocess.run` How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secure coding for SG Government: AS + CK controls
The ICT&SS Policy Reform (IM8's successor) Cybersecurity Control Catalog contains 15 Application Security (AS) controls and 4 Cryptography/Key Management (CK) controls that land directly in application code. This skill maps them to coding decisions so an agent writing or reviewing code produces compliant output the first time, with control IDs the agency's security team can trace to its System Security Plan (SSP).
Use this skill in three modes:
- Writing new code: apply the scenario sections below as you write.
- Reviewing a diff: run the review checklist against every changed file; flag violations with the control ID.
- Auditing a codebase: sweep for each checklist row; report findings per control ID with file:line references.
Source and currency
Control text in this skill and in references/as-controls.md is embedded from info.standards.tech.gov.sg as of 2026-07-16. The standards iterate actively. For compliance-critical decisions (SSP evidence, audit responses, deviations), verify against the live pages:
- AS family: https://info.standards.tech.gov.sg/control-catalog/cybersecurity/as/
- CK family: https://info.standards.tech.gov.sg/control-catalog/cybersecurity/ck/
- SSP profiles (control levels): https://info.standards.tech.gov.sg/ssp/
Machine-readable OSCAL: https://github.com/GovtechSG/tech-standards is useful for tooling but lags the site; the site is authoritative.
Before you start: levels and parameters
- Levels come from the project's SSP, not the catalog. Level 0 = mandatory, no deviation. Level 1 = default; deviations need documented IDSC/CIO/CISO approval. Level 2 = risk-based best practice. In the Medium-Risk Cloud SSP, AS-1, AS-3, AS-7 and AS-8 are Level 0 (promoted from Level 1 in low-risk); AS-10, AS-12, AS-13, AS-14 sit at Level 2 in both cloud SSPs; CK-1/CK-2 are Level 1 in medium-risk. Use the sibling skill sg-gov-ssp-navigator to determine the applicable SSP and each control's level for this system. Treat every control below as required unless the SSP says otherwise.
- Parameters are agency-defined.
as-5_prm_1/2/3(password length, policy, type),as-11_prm_1/2(session hours, session type),ck-2_prm_1(key rotation days) have no catalog values. Never invent them. Ask the user for the project's SSP parameter values, or locate them in the repo (SSP document, security config, compliance docs). If unavailable, implement against a named configuration constant, flag it asTODO(SSP): confirm as-5_prm_1, and say so in your report.
What ships with it
4 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.
- 7d ago First seen · 306 lines · 156 tokens per session scan A 32ab4ae54313
sg-gov-secure-coding-as is a skill published in the GitHub repository kyleoliveiro/sg-gov-skills (17 stars, last pushed 7d ago), licensed MIT. It adds 156 tokens to every session and 4,591 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-03.
sg-gov-secure-coding-as compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sg-gov-secure-coding-askyleoliveiro/sg-gov-skills | Skill | 17 | 7d ago | MIT | A | 156 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.5k | today | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 4d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.3k | today | MIT | A | 49 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 949 | yesterday | MIT | A | 84 | Claude Code |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 51 | Claude Code, Codex |
| explore-unknownsdzhng/skills | Skill | 1.5k | yesterday | MIT | A | 162 | Claude Code, Codex |