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 agentmods add instructions/sdcorejs/sdcorejs-agent/claude-mdgit clone --depth 1 https://github.com/sdcorejs/sdcorejs-agentWhat 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 | $0.03457 | $0.03457 |
| Opus 5 | $0.01729 | $0.01729 |
| Sonnet 5 | $0.00691 | $0.00691 |
| Haiku 4.5 | $0.00346 | $0.00346 |
Grade A, and why
sdcorejs-agent CLAUDE.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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDCoreJS SDLC Agent - Claude Code Instructions
Claude Code entry point for the SDCoreJS skill pack. The same skill model is mirrored to Codex, Cursor, and Copilot through their entry files.
This repo provides Runtime-localized engineering skills for developers and technical teams working across the software delivery lifecycle:
- Angular portals with
@sdcorejs/angular - NestJS + Postgres backends
- Next.js public sites
- Governed AI-agent application contracts and implementations
- A product track for PO-facing docs plus feature ledgers and traceability
- A design track for FE handoff artifacts from product user stories
- A first-class test track
- A generic execution harness for unsupported stacks or non-track plans
Skill Source Language
Author this skill pack in English only. skills/**, _refs/**, prompts,
templates, examples, generated mirrors, and validation fixtures must not embed
Vietnamese prose or Vietnamese-only sample UI text. Runtime localization belongs
to the consuming project/session: instructions may say to translate or localize
output at runtime, but the reusable skill source itself stays English and
locale-neutral. Use placeholders such as <localized label> instead of concrete
Vietnamese labels.
Localization test prompts may use non-English input when they are explicitly fixtures for dispatch/runtime-localization behavior. Expected source text, generated mirrors, reusable examples, and expected generated skill prose must remain English-only and locale-neutral.
Dispatch
At session start, glob skills/**/*.md, excluding _refs/**, and read frontmatter only. Match user requests against each skill description. Read the selected skill body before acting.
Resolve tracks, stack profiles, repository roles, artifact ownership, review/
repair/ship support, and evidence classes from the versioned
_refs/shared/system-registry.json. A capability profile refines an approved
track; it is not a track. Keep the semantic artifact owner separate from the
execution host, and never use the current working directory to infer ownership.
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 First seen · 267 lines · 3,457 tokens per session scan A 6f47a937603a
sdcorejs-agent CLAUDE.md is an instructions file published in the GitHub repository sdcorejs/sdcorejs-agent (2 stars, last pushed 15d ago), licensed MIT. It adds 3,457 tokens to every session, about $0.0173 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.