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 jxoesneon/Ciel --skill dispatching-parallel-agentsgit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/dispatching-parallel-agents)<a href="https://agentmods.dev/skills/jxoesneon/ciel/dispatching-parallel-agents"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/dispatching-parallel-agents/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/jxoesneon/ciel/dispatching-parallel-agents"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/dispatching-parallel-agents.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 | $0.00023 | $0.00764 |
| Opus 5 | $0.00012 | $0.00382 |
| Sonnet 5 | $0.00005 | $0.00153 |
| Haiku 4.5 | $0.00002 | $0.00076 |
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 8d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIEL ADAPTATION: Dispatching Parallel Agents (Concurrency Mandate)
This skill formalizes CIEL's approach to concurrency. When the Orchestrator identifies multiple independent tasks (e.g., unrelated bug fixes, distinct test file failures), it MUST dispatch specialized sub-agents in parallel rather than executing them sequentially.
Integration Context
Adapted from ~/.agents/skills/dispatching-parallel-agents/. This is an advanced execution strategy that builds upon subagent-driven-development. While the base skill focuses on isolating context per task, this skill focuses on executing those isolated contexts concurrently to minimize overall turn latency.
The Concurrency Decision Matrix
Before dispatching in parallel, the Orchestrator MUST evaluate the tasks against these conditions:
🟢 Proceed with Parallel Dispatch IF:
- Tasks operate on distinct, non-overlapping files or subsystems.
- Fixing/implementing Task A has zero theoretical impact on Task B.
- The root causes or requirements are entirely independent.
🔴 Fallback to Sequential Dispatch IF:
- Tasks require modifying the same files (Shared State).
- Tasks are sequentially dependent (Task B relies on the output of Task A).
- The Orchestrator does not fully understand the system state and is performing exploratory debugging.
Orchestration Workflow
- Identify Domains: Group failures or requirements into strictly independent domains. Check the Knowledge Graph (
mempalace_kg_query) for historical implicit dependencies between these domains. - Contextualize: Craft a highly specific, self-contained prompt for each domain. Include the exact error messages, file paths, and success criteria.
- Dispatch: Invoke the sub-agents (e.g., via the
generalisttool withoutwait_for_previousset to true) concurrently. - Integration Review:
- As agents return, read their execution summaries.
- Run the
verification-loop(full test suite) to ensure the parallel fixes did not introduce emergent conflicts.
- Evolutionary Feedback (Failure Memory): If parallel agents produce a silent semantic collision or integration failure despite operating on "non-overlapping" files, the Orchestrator MUST log this implicit dependency to the Knowledge Graph (
mempalace_kg_adde.g., 'Module A' 'implicitly_depends_on' 'Module B') to prevent future parallel dispatch of these specific domains.
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.
- 8d ago First seen · 62 lines · 23 tokens per session scan A 1b056b3dac49
dispatching-parallel-agents is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 23 tokens to every session and 764 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
surge
Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…
ai-native-software-dev
Use when the user asks to build, change, modernize, or reconstruct non-trivial software with an AI-native workflow, including greenfield development, work in an existing codebase, or authorized reference-based product reconstruction; also use when lifecycle planning, architecture, implementation, testing, review…
Code Quality Review
Conduct a comprehensive code quality review focused on clean code, architecture, and project standards.
ticket-spec
Turn a raw Linear Triage ticket into a fully specified ai:agent-ready one by exploring the codebase. Use when specifying, refining, or promoting tickets, or when asked why a ticket isn't dispatchable.
redpolicy-guide
An editorial policy for turning webinar transcripts into self-contained guides. A transcript is a written record of spoken material, while a self-contained guide can be understood without watching the webinar.
write-overview
A workflow for researching and writing a review essay about a project topic when no finished source text exists. It gathers the facts, studies example essays when available and produces the article in a project output folder.