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 skills/sdcorejs/sdcorejs-agent/sdcorejs-parallel-dispatchnpx skills add sdcorejs/sdcorejs-agent --skill sdcorejs-parallel-dispatchgit 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 | $0.00081 | $0.03237 |
| Opus 5 | $0.00041 | $0.01618 |
| Sonnet 5 | $0.00016 | $0.00647 |
| Haiku 4.5 | $0.00008 | $0.00324 |
Grade A, and why
sdcorejs-parallel-dispatch 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Dispatch
Shared Protocols
Read _refs/shared/runtime-protocols.md and the complete
_refs/orchestration/parallel-protocol.md; use its deterministic validators
rather than reimplementing them in prompts. For write-capable work, load
_refs/orchestration/workspace-isolation.md and assign one owner for every
shared artifact. Verify plan identity with
_refs/shared/approved-artifact.mjs, resolve roles/tracks through
_refs/shared/system-registry.json, and build every unit envelope with
_refs/orchestration/parallel-protocol.mjs. Load
_refs/harness/delegation-policy.json and
_refs/harness/task-brief.md only after dispatch is feasible.
Purpose
This skill is the fail-closed gate for parallel work. It validates a protocol-v2 contract, classifies the dependency topology, dispatches only mechanically safe units, integrates immutable or exact-diff results deterministically, and runs global verification plus the final read-only branch-ready gate.
The public compatibility verdicts remain:
SEQUENTIALPARALLEL-CANDIDATEROLE-SPLIT
The underlying topology is one of READ_ONLY_FANOUT,
INDEPENDENT_WRITE_UNITS, CONTRACT_BOUND_ROLES, or SEQUENTIAL_DAG.
Parent write permission is narrow: it may write an approved, change-scoped
protocol artifact under the target .sdcorejs/ area and may apply validated
unit results in the integration workspace. Runtime task_brief and
review_package messages stay in the harness/thread and never become mutable
.sdcorejs/** checkpoints. The parent does not own implementation files.
Workers may create only approved change-scoped artifacts and must not update
summary, persona, memory, or living track backlogs. The named
integration owner updates shared artifacts once after fan-in and emits the
merged artifact_context. Shared implementation paths belong to a concrete
unit; shared/coordinated files and module gitlinks belong only to the named
integration-unit. parent-contract-only owns contract metadata only.
In the read-only contract, the parent and units make no writes.
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 · 303 lines · 81 tokens per session scan A 2dd6ad2ba307
sdcorejs-parallel-dispatch is a skill published in the GitHub repository sdcorejs/sdcorejs-agent (2 stars, last pushed 15d ago), licensed MIT. It adds 81 tokens to every session and 3,237 once invoked, about $0.0004 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 skills, from other repositories
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
skill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
geo-audit
Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, content quality, and schema markup. Produces a composite GEO Score (0-100) with prioritized action plan.
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
skill-creator
Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.