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 krzysztofsurdy/code-virtuoso --skill dispatching-parallel-agentsgit clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote 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/krzysztofsurdy/code-virtuoso/dispatching-parallel-agents)<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/dispatching-parallel-agents"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/dispatching-parallel-agents.svg" alt="Measured on agentmods" 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 | $0.00154 | $0.03311 |
| Opus 5 | $0.00077 | $0.01656 |
| Sonnet 5 | $0.00031 | $0.00662 |
| Haiku 4.5 | $0.00015 | $0.00331 |
Grade A, and why
dispatching-parallel-agents 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 7d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatching Parallel Agents
Effective orchestration means knowing when to do work yourself and when to delegate it to focused subagents working in parallel. The core insight is simple: independent work should happen concurrently, not sequentially. But "independent" is the load-bearing word - getting decomposition wrong turns parallel execution into a coordination nightmare.
Core Principles
| Principle | Meaning |
|---|---|
| Independence over coordination | If two tasks share state, they are one task. Only dispatch work that can complete without cross-agent communication. |
| Precision over hope | A subagent brief must be specific enough that the agent cannot misinterpret its scope. Vague briefs produce vague results. |
| Isolation over sharing | Each subagent starts with a clean context. It receives exactly what it needs - nothing inherited, nothing ambient. |
| Synthesis over concatenation | The orchestrator's job is not to paste outputs together. It is to resolve conflicts, deduplicate, and produce a coherent whole. |
| Fail fast over fail silent | Every dispatch includes a failure mode. Subagents report blockers immediately rather than guessing past them. |
When to Parallelize
| Signal | Example |
|---|---|
| Multiple independent areas of investigation | "How does auth work?" + "How does billing work?" - no shared code path |
| Research spanning distinct topics | Investigating a framework upgrade requires checking breaking changes, dependency compatibility, and test coverage separately |
| Implementation across non-overlapping files | Backend API + frontend component + database migration touching different file sets |
| Review of independent subsystems | Running a reviewer on module A while running a refactor scout on module B |
| Repetitive tasks with different inputs | Auditing 5 services for security vulnerabilities - same process, different targets |
When NOT to Parallelize
| Signal | Why Sequential Is Better |
|---|---|
| Output of task A is input to task B | Pipeline dependency - parallelize within stages, not across them |
| Tasks modify overlapping files | Merge conflicts are inevitable and expensive to resolve |
| Understanding requires full context | Splitting a single complex investigation loses the thread |
| The problem is not yet understood | Parallelize execution, not exploration of unknowns |
| Fewer than 3 independent units | Dispatch overhead exceeds time saved |
| Results must be strictly ordered | Sequential execution preserves natural ordering without post-processing |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 280 lines · 154 tokens per session scan A 701857cd0cf1
dispatching-parallel-agents is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (20 stars, last pushed 3mo ago), licensed MIT. It adds 154 tokens to every session and 3,311 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
hermes-diagnostic-review
Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls, and repeated fixes, then propose suggestion-only improvements and reusable skills. Human-gated; never auto-applies.
instruction-eval
Change one condition an agent runs under (instruction text, the reference material instructions point at, MCP tools and permissions, hooks, skill files), then run the same prompts before and after, several times each, to see what actually changes. Produces an HTML report showing both arms' answers side by side. Use…
worth-building
Decide how elaborate to build something (simple vs. robust) and return a concrete, PoC-shaped proposal at that level — not over- or under-engineered, but right-sized. Use whenever someone is building something and the investment level is unclear: "quick or proper?", "MVP vs. real product", "is this over-engineering?"…
django-ticket-triage
Analyze a Django Trac ticket and produce a triage recommendation report — duplicate search, related PRs, forum threads, and the affected source code. Use when the user gives a Django ticket number, or asks whether a ticket is valid, a duplicate, or ready for a triage stage.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
healthcheck
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).