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 skills add sdcorejs/sdcorejs-agent --skill sdcorejs-subagent-driven-developmentgit 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/skills/sdcorejs/sdcorejs-agent/sdcorejs-subagent-driven-development)<a href="https://agentmods.dev/skills/sdcorejs/sdcorejs-agent/sdcorejs-subagent-driven-development"><img src="https://agentmods.dev/badge/skills/sdcorejs/sdcorejs-agent/sdcorejs-subagent-driven-development/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/skills/sdcorejs/sdcorejs-agent/sdcorejs-subagent-driven-development"><img src="https://agentmods.dev/badge/skills/sdcorejs/sdcorejs-agent/sdcorejs-subagent-driven-development.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 | $0.00072 | $0.01657 |
| Opus 5.5 | $0.00029 | $0.00663 |
| Sonnet 5.5 | $0.00014 | $0.00331 |
| Haiku 4.5 | $0.00007 | $0.00166 |
Grade A, and why
sdcorejs-subagent-driven-development 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 16d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Path resolution: Resolve ../../_refs/... relative to this SKILL.md. Resolve another SDCoreJS skill by opening the sibling folder ../<skill-name>/SKILL.md.
Subagent-Driven Development
Purpose
Own how an approved plan is executed through fresh worker contexts. Keep worker context isolation, unit review, owner-scoped repair, and deterministic fan-in consistent whether ready units run concurrently or one at a time.
sdcorejs-parallel-dispatch is the low-level safety scheduler: it decides which
ready units may overlap and enforces path, resource, workspace, failure, and
fan-in rules. This skill owns the higher-level development lifecycle around that
decision. Do not rename or duplicate the scheduler.
Preconditions
For write-capable work, require an immutable approved plan and a verified
plan_context. A direct request to delegate unapproved implementation returns
to sdcorejs-plan; it is not a planning bypass. Read-only parallel reviews or
audits route directly to sdcorejs-parallel-dispatch.
A missing, stale, or legacy project summary is not a gate. Continue with targeted source reads or a scoped code map before dispatch, and never infer missing facts.
Read these references completely before dispatch:
../../_refs/shared/runtime-protocols.md../../_refs/harness/runtime-attestation.md../../_refs/harness/delegation-policy.json../../_refs/harness/task-brief.md../../_refs/orchestration/parallel-protocol.md../../_refs/orchestration/workspace-isolation.mdfor write-capable isolated units
Use ../../_refs/harness/runtime-attestation.mjs for current-session capability
evidence and compileParallelContext from
../../_refs/orchestration/parallel-protocol.mjs for the dependency waves and
parallel opportunity report.
Execution workflow
1. Verify and compile
- Verify approved spec/plan identity, source revision, repository ownership,
allowed/prohibited paths, dependency/env/migration boundaries, and working
tree state exactly as
sdcorejs-execute-planrequires. - Attest delegation, concurrent dispatch, worker-CWD binding, native/manual worktree support, cancellation, result refs, and effective maximum concurrency from current-session evidence. Unknown stays unknown.
- Compile compact
parallel_candidates.unitsinto dependency waves and the opportunity report. Complete workspace, dispatch-envelope, integration, verification, failure, and final-tail fields before any write dispatch. - Preserve the approved
execution_policy:parallel-preferredselects safe concurrent waves and degrades safely;sequentialuses sequential fresh workers;autoselects concurrent waves only when the report proves positive benefit and every safety gate passes.
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.
- 16d ago Changed · +2 lines 03d61de29735
- 1mo ago First seen · 167 lines · 72 tokens per session scan A e8ae8740cb05
sdcorejs-subagent-driven-development is a skill published in the GitHub repository sdcorejs/sdcorejs-agent (2 stars, last pushed 15d ago), licensed MIT. It adds 72 tokens to every session and 1,657 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…