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/miaoy0ushan/fp/dispatch-parallel-domainsnpx skills add MiaoY0uShan/FP --skill dispatch-parallel-domainsgit clone --depth 1 https://github.com/MiaoY0uShan/FPWrote 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/miaoy0ushan/fp/dispatch-parallel-domains)<a href="https://agentmods.dev/skills/miaoy0ushan/fp/dispatch-parallel-domains"><img src="https://agentmods.dev/badge/skills/miaoy0ushan/fp/dispatch-parallel-domains.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 | $0.00047 | $0.00477 |
| Opus 5 | $0.00023 | $0.00238 |
| Sonnet 5 | $0.00009 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
fp-dispatch-parallel-domains 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 6d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FP Dispatch Parallel Domains
Parallelize independent problem domains, not merely a long task list.
Independence Gate
Before fan-out, give every candidate domain an ID and prove all of the following:
- no domain consumes another domain's unfinished output;
- writer paths and workspaces are disjoint, or the domains are read-only;
- there is no shared state, lock, cache, database, service, device, generated output, manifest, lockfile, or mutation lease;
- failures and rollback in one domain cannot invalidate another domain's evidence;
- each domain has its own acceptance rows and can return a bounded result envelope.
If any claim is unknown, keep the domains serial. Shared state, files, or generated output must be serial. Apparent directory separation is insufficient when build metadata or runtime state is shared.
Fan-Out
Freeze the domain DAG, ownership map, active-concurrency limit, cumulative-thread budget, and stable task-input order. Enforce one writer per owned path set by dispatching at most one active writer for it. Under delegated execution, each domain owns its own fresh implementer/reviewer/fixer chain; the parent remains the only cross-domain integrator.
Parallel read-only probes may share immutable inputs. Parallel writers require disjoint paths and isolated mutable resources. Never parallelize live-system mutations, credential use, deployment, external messaging, or memory promotion.
Fan-In
Wait for every dispatched domain to become terminal. Integrate results in declared task-input order, not completion order. Reconcile interface assumptions and consumer/provider edges, then run parent-side cross-domain checks and a negative control. A domain failure remains explicit; it is not hidden by successful siblings.
If integration exposes coupling, cancel stale pending work, collapse the affected domains into a serial chain, and issue fresh envelopes. Do not reuse a completed domain agent as another domain's implementer or reviewer.
Negative Control
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.
- 6d ago First seen · 37 lines · 47 tokens per session scan A 5c69ba5245c5
fp-dispatch-parallel-domains is a skill published in the GitHub repository MiaoY0uShan/FP (3 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 477 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 2026-08-31.
Other skills, from other repositories
kami-deck
A lab-meeting deck on gut-microbiome links to sleep quality — the design, the results, the caveats, and the next experiment. Built as a decision-grade academic research deck for lab group, PI.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
fs-editorial-forest
Art-directing a fashion house's annual report — the editorial system, the photography rhythm, and the data spreads. Built as a decision-grade design craft deck for brand stakeholders, exec audience.
html-ppt-zhangzara-stencil-tablet
A workplace-safety compliance review for a manufacturing regulator — findings, the evidence chain, and the corrective mandate. Built as a decision-grade policy briefing deck for regulator, plant leadership.
simple-deck
OpenDesign's operating review: growth, burn, and the concrete path to sustainability without losing the open ethos. Built as a decision-grade corporate strategy deck for leadership team.
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.