sdcorejs-agent AGENTS.md

Repository instructions for an engineering skill pack covering product work, design, testing, documentation, code review, and delivery across several web technologies.

In plain words
What is it for?
Use it to guide governed requirements, user stories, technical implementation, tests, reviews, documentation, and delivery plans in supported or generic projects.
Why use it?
It provides a shared workflow and language policy for teams using AI assistants throughout software development.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/sdcorejs/sdcorejs-agent/agents-md
Clone the repo
git clone --depth 1 https://github.com/sdcorejs/sdcorejs-agent

Made for: Codex, OpenCode.

Per session 2,350 This file is loaded in full into every session.
When invoked 2,350 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02350 $0.02350
Opus 5 $0.01175 $0.01175
Sonnet 5 $0.00470 $0.00470
Haiku 4.5 $0.00235 $0.00235

Measured 2d ago against content hash 32a84f06b3a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdcorejs-agent 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 2d 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.

AGENTS.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDCoreJS SDLC Agent

Entry point for AGENTS.md-aware tools: Codex, Cursor, OpenAI Agents SDK, and compatible assistants. Claude Code reads CLAUDE.md; Copilot reads .github/copilot-instructions.md.

This repository is an engineering skill pack for developers and technical teams. Its root Node workspace is private and validation-only. Its 22 public skills cover governed requirements, product, design, tests, Angular, NestJS, Next.js, AI-agent contracts, documentation, review, delivery, and a generic harness for other stacks.

All user-facing behavior is Runtime-localized: detect the user's language, respond in that language, and preserve locale-specific marks. Keep identifiers, permission codes, env keys, and route paths in English.

Skill Source Language

Author skills/**, _refs/**, prompts, templates, reusable examples, and generated mirrors in English only. Runtime localization belongs to the consuming project/session; use locale-neutral placeholders such as <localized label> in reusable sources.

Localization test prompts may use non-English input when they are explicitly fixtures for dispatch/runtime-localization behavior. Expected source text and generated prose remain English-only and locale-neutral.

Dispatch

Dispatch by name: frontmatter and the description: trigger. Load only frontmatter at session start; read a skill body only after selecting that skill.

Use _refs/shared/system-registry.json as the versioned source for tracks, stack profiles, artifact kinds, repository roles, review/repair/ship support, and evidence classes. Keep track, stack profile, capability profile, artifact owner, repository role, and execution host as separate fields. The current working directory is never evidence of artifact ownership.

When multiple skills match, apply this priority before reading a body:

  1. Explicit skill name from the user.
  2. Approved spec: architecture when required; approved plan: sdcorejs-execute-plan.
  3. Product, design, or direct test work: sdcorejs-product, sdcorejs-design, or sdcorejs-test; failing-test diagnosis uses sdcorejs-debug.
  4. Dedicated utility intent: sdcorejs-simplify, sdcorejs-explore, sdcorejs-documentation, sdcorejs-review, sdcorejs-repair-loop, sdcorejs-debug, sdcorejs-ship, or sdcorejs-git.
  5. Confirmed track implementation: sdcorejs-ai-agent, sdcorejs-angular, sdcorejs-nestjs, or sdcorejs-nextjs.
  6. Open-ended, ambiguous, or under-specified scope: sdcorejs-brainstorming.

Read the full file on GitHub · 195 lines

Changes

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.

  1. 2d ago First seen · 195 lines · 2,350 tokens per session scan A 32a84f06b3a9

Subscribe to this mod's changes

sdcorejs-agent AGENTS.md is an instructions file published in the GitHub repository sdcorejs/sdcorejs-agent (2 stars, last pushed 15d ago), licensed MIT. It adds 2,350 tokens to every session, about $0.0118 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens