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.
git clone --depth 1 https://github.com/sdcorejs/sdcorejs-agentWrote 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/agents/sdcorejs/sdcorejs-agent/sdcorejs)<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.
<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>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 | $0.00031 | $0.01412 |
| Opus 5 | $0.00015 | $0.00706 |
| Sonnet 5 | $0.00006 | $0.00282 |
| Haiku 4.5 | $0.00003 | $0.00141 |
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.
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.
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.
- 5d ago First seen · 129 lines · 31 tokens per session scan A 804434b8d584
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.