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 nxtg-ai/forge-plugin --skill parallel-executiongit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWrote 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/nxtg-ai/forge-plugin/parallel-execution)<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/parallel-execution"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/parallel-execution/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/nxtg-ai/forge-plugin/parallel-execution"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/parallel-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.02480 |
| Opus 5.5 | $0.00035 | $0.00992 |
| Sonnet 5.5 | $0.00017 | $0.00496 |
| Haiku 4.5 | $0.00009 | $0.00248 |
Grade A, and why
Parallel Execution 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 1mo 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Execution: Plan Mode + Agent Teams
Two superpowers. Plan Mode thinks before it writes. Agent Teams fan work out
across parallel subagents. Combine them for complex features. The agent roster and
routing rules in §5 are the source of truth for Task delegation — the subagent_type
must match a name: from that table exactly.
1. PLAN MODE
Explore (reads only) → Draft plan → Present → Wait for approval → Execute
- Explore only — Read, Glob, Grep, read-only Bash. No writes until approved.
- Draft a plan — scope, files affected, approach, boundaries.
- Present — show the plan in chat, ask for approval.
- Wait — do not proceed until the user says "proceed" / "yes" / "looks good".
- Execute — now write, edit, spawn agents.
Plan document format
## Plan: {task name}
**Scope:** what will change
**Files to create / modify / NOT touch:** (the last is a boundary declaration)
**Approach:** brief
**Risks / trade-offs:** if any
Proceed? (yes / modify / cancel)
When to invoke
| Situation | Plan Mode? |
|---|---|
| Touching 3+ files | Yes |
A --fix command (show what changes before writing) |
Yes — always |
| Architectural change | Yes |
| Single-file bug fix / comment / answering a question | No |
Anti-patterns
- Writing files during Explore.
- Presenting a plan then executing without waiting.
- Skipping the plan for a "quick" task that touches 3+ files.
- Modifying files outside the declared scope.
2. AGENT TEAMS
Invocation
Task tool:
subagent_type: "builder" ← must match a name: in §5 exactly (kebab-case)
prompt: "Self-contained task. Declare file boundaries. State: no writes / writes X only."
run_in_background: false ← true only if you have real work to do while it runs
Pattern A — Fan-Out Analysis (read-only, N dimensions in parallel)
Task(detective, "Analyze test coverage in src/. Report gaps only. No writes.")
Task(security, "Scan src/ for OWASP issues + secrets. Report only. No writes.")
Task(performance,"Profile src/ hotspots. Report only. No writes.")
↓ all run concurrently ↓
Aggregate the three reports into one.
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.
- 1mo ago First seen · 227 lines · 87 tokens per session scan A 1b5ea727a764
Parallel Execution is a skill published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 2,480 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 2026-09-03.
Other skills, from other repositories
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
error-analysis
Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.
dev
One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.
accessibility
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…