Borrowing it
Nothing to install: this file belongs to kyleoliveiro/sg-gov-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kyleoliveiro/sg-gov-skills/main/AGENTS.mdgit 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/instructions/kyleoliveiro/sg-gov-skills/agents-md)<a href="https://agentmods.dev/instructions/kyleoliveiro/sg-gov-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/kyleoliveiro/sg-gov-skills/agents-md/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/instructions/kyleoliveiro/sg-gov-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/kyleoliveiro/sg-gov-skills/agents-md.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 | $0.00515 | $0.00515 |
| Opus 5.5 | $0.00206 | $0.00206 |
| Sonnet 5.5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
sg-gov-skills AGENTS.md 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 yesterday.
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 — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent skills for developers building tech projects for Singapore government agencies.
The skills cover the requirements specific to government delivery: the ICT&SS Policy Reform (IM8's successor) and its System Security Plans, the Cybersecurity and Digital Service Standards control catalogs, Singpass, Corppass, and Myinfo integration, SGDS, and WCAG 2.2 accessibility. Each skill is small, covers one concern, and must work with any agent and model.
Repository layout
skills/<skill-name>/SKILL.md: the published skills. This is the layout theskillsCLI discovers, so consumers install withnpx skills add kyleoliveiro/sg-gov-skills. Authoring conventions live inskills/README.md..claude-plugin/marketplace.json: groups published skills in the interactiveskillsCLI installer. Every skill must appear in exactly one group.scripts/: the eval dataset validator and the trigger-eval runner..agents/skills/and.claude/skills/: third-party skills installed locally for authoring (skill-creator, humanizer). Gitignored; tracked inskills-lock.jsonand restored withnpx skills experimental_install(ornpm run skills:restore).
Working on skills
- One skill per delivery concern; kebab-case folder names prefixed with
sg-gov-(thenamefrontmatter matches the folder). - Use the skill-creator skill to scaffold and iterate; validate with
npm run skills:validate -- skills/<skill-name>. - Task-performance scenarios live in
skills/<skill-name>/evals/evals.json; description-trigger queries live separately inskills/<skill-name>/evals/trigger-evals.json. - Validate every skill's task and trigger datasets locally with
npm run skills:evals:validate(each skill needs both files: at least two task scenarios, and 20 trigger queries split 10 positive / 10 negative). - Run description-trigger evals with
npm run skills:eval -- <skill-name>(extrarun_evalflags pass through, e.g.--runs-per-query 3); run with no args to list skills that have trigger sets. Trigger evals shell out toclaude -p, so they consume real usage. - When adding a skill, also add it to the appropriate catalog table in
README.mdand installer group in.claude-plugin/marketplace.json.
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.
- yesterday Changed · +19 tokens per session db7b805429ea
- 8d ago Changed · +1 lines · -26 tokens per session 0b662c41e1df
- 2mo ago First seen · 19 lines · 522 tokens per session scan A 54e5490b649b
sg-gov-skills AGENTS.md is an instructions file published in the GitHub repository kyleoliveiro/sg-gov-skills (17 stars, last pushed 2d ago), licensed MIT. It adds 515 tokens to every session, about $0.0021 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.