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 subagent-driven-developmentgit 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/subagent-driven-development)<a href="https://agentmods.dev/skills/jxoesneon/ciel/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/subagent-driven-development/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/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/subagent-driven-development.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 | $0.00028 | $0.00716 |
| Opus 5 | $0.00014 | $0.00358 |
| Sonnet 5 | $0.00006 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
subagent-driven-development 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 9d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIEL ADAPTATION: Subagent-Driven Development (Delegation Mandate)
This skill formalizes CIEL's orchestration philosophy regarding context management and task execution. To preserve the Orchestrator's context window, independent implementation tasks MUST be delegated to fresh, ephemeral sub-agents (e.g., the generalist tool or specific skill agents).
Integration Context
Adapted from ~/.agents/skills/subagent-driven-development/. This skill represents the transition from the Strategy Layer (make-plan) to the Execution Layer (do).
The Core Loop (Per Task)
When executing an approved implementation plan, the Orchestrator executes the following loop for each discrete task:
1. Dispatch (The Implementer)
- Extract the specific task, relevant context, and strict acceptance criteria from the plan.
- Dispatch a sub-agent (e.g.,
generalist) with a highly focused prompt. - Rule: Do NOT pass the entire session history. Pass ONLY what the sub-agent needs to succeed.
2. Stage 1: Spec Compliance Review (The Verifier)
- Once the Implementer returns, the Orchestrator (or a secondary sub-agent) evaluates the diff strictly against the original task specification.
- Goal: Did it build exactly what was asked, without over-engineering (YAGNI) or missing requirements?
- If it fails, dispatch a sub-agent to fix the specific gaps.
3. Stage 2: Code Quality Review (The Auditor)
- After Spec Compliance is verified, evaluate the diff against CIEL's
coding-standards. - Goal: Is it readable? Does it respect immutability? Are there code smells (deep nesting, long functions)?
- If it fails, dispatch a sub-agent to refactor for quality.
Orchestrator Responsibilities
- Blocker Resolution: If a sub-agent reports it is
BLOCKEDorNEEDS_CONTEXT, the Orchestrator must analyze the failure, gather the missing context (usingread_file,grep_search, etc.), and re-dispatch with a refined prompt. Do NOT attempt to manually implement the fix in the main session. - Sequential Safety: Ensure tasks that depend on the same files are not dispatched concurrently to avoid race conditions.
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.
- 9d ago First seen · 63 lines · 28 tokens per session scan A 37efd658c907
subagent-driven-development is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 28 tokens to every session and 716 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.
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.
redpolicy-article
An editorial guide for writing comparison articles about services, tools, and products. It defines a consistent entry format covering the name, link, price, description, and notable features.