sdcorejs

sdcorejs is an agent for GitHub Copilot from sdcorejs/sdcorejs-agent. It costs 31 tokens per session (1,412 once invoked), scanned A, original, MIT.

A chat mode for managing software work with the SDCoreJS skill pack. It guides work from brainstorming and an approved plan through implementation, tests, review, documentation, and release checks.

In plain words
What is it for?
Use it to plan and execute product, design, testing, Angular, NestJS, Next.js, or general coding-agent tasks through a staged workflow.
Why use it?
It separates deciding what to build from carrying out changes, and defines when work may be delegated or must return to planning.

Agent for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt. Also seen: model in frontmatter; mentions subagents; mentions Codex.

Good fit Use it to plan and execute product, design, testing, Angular, NestJS, Next.js, or general coding-agent tasks through a staged workflow.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sdcorejs/sdcorejs-agent/sdcorejs
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.

Clone the repo
git clone --depth 1 https://github.com/sdcorejs/sdcorejs-agent

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for sdcorejs

README.md
[![agentmods](https://agentmods.dev/badge/agents/sdcorejs/sdcorejs-agent/sdcorejs/github.svg)](https://agentmods.dev/agents/sdcorejs/sdcorejs-agent/sdcorejs)
Your own site
<a href="https://agentmods.dev/agents/sdcorejs/sdcorejs-agent/sdcorejs"><img src="https://agentmods.dev/badge/agents/sdcorejs/sdcorejs-agent/sdcorejs/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.

agentmods 80×15 button for sdcorejs

Your own site · 80×15
<a href="https://agentmods.dev/agents/sdcorejs/sdcorejs-agent/sdcorejs"><img src="https://agentmods.dev/badge/agents/sdcorejs/sdcorejs-agent/sdcorejs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,412 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00031 $0.01412
Opus 5 $0.00015 $0.00706
Sonnet 5 $0.00006 $0.00282
Haiku 4.5 $0.00003 $0.00141

Measured 5d ago against content hash 804434b8d584, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-13, from the pricing page.

Security

Grade A, and why

sdcorejs 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 5d 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.

.github/chatmodes/sdcorejs.chatmode.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDCoreJS SDLC Chat Mode

Use the SDCoreJS skill pack. Runtime-localized output is required.

Use _refs/shared/system-registry.json for track/profile/repository/evidence semantics. Keep semantic artifact ownership separate from the execution host; never infer ownership from the current working directory.

Workflow

sdcorejs-brainstorming
-> sdcorejs-spec (approval gate + approved spec snapshot)
-> sdcorejs-plan (approval gate + approved plan snapshot)
-> sdcorejs-execute-plan
-> executor: ai-agent | Core UI angular | nestjs | nextjs | product | design | test | generic harness
-> finish gate and tail chain
   tests -> optional sdcorejs-simplify -> affected focused tests
   -> review/repair -> documentation/task/memory -> ship gates

sdcorejs-execute-plan attests delegation and concurrency separately and preserves the approved execution policy. Direct delegated execution of an approved plan uses sdcorejs-subagent-driven-development: safe waves run through the low-level sdcorejs-parallel-dispatch scheduler, unsafe waves use sequential fresh workers, and parent execution is the last fallback.

Unapproved write work returns to planning. Read-only parallel review/audit uses a read-only-request contract with writes denied. Write-capable dispatch uses working-tree preflight, mechanical ownership/isolation validation, deterministic fan-in, and the mandatory final verification tail.

Pure Q&A answers directly. A bounded low-risk fix may use targeted context, smallest edit, focused verification, and concise review; scope growth escalates to the full workflow. Unsupported or unknown native capabilities use portable numbered Markdown and sequential parent fallbacks.

Mandatory Execution Discipline

For any non-trivial execution task, the agent MUST use _refs/shared/tasklist.md.

Create outcome-based progress before work starts and update it only for a meaningful outcome, scope change, blocker, verification phase, decision, or status request.

This applies across explore, git, review, debug, ship, dependency updates, code modification, PR/changelog generation, and verification-before-done.

Read the full file on GitHub · 129 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. 5d ago First seen · 129 lines · 31 tokens per session scan A 804434b8d584

Subscribe to this mod's changes

sdcorejs is an agent published in the GitHub repository sdcorejs/sdcorejs-agent (2 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 1,412 once invoked, about $0.0002 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 2026-09-08.