An orchestration system for coding-agent skills that selects, combines, researches, and updates capabilities across supported agent environments.

It helps route tasks to suitable skills, set up the system for a detected agent environment, combine skills into workflows, and maintain their versions and memory.

It reduces the need to choose and manage skills manually when a task needs several capabilities. It also keeps shared and project-specific skill data organized and checks its integrity.

ciel — Skill for Claude Code and Codex by jxoesneon

Install

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.

Any agent

npx skills add jxoesneon/Ciel --skill ciel.skill

Clone the repo

git clone --depth 1 https://github.com/jxoesneon/Ciel

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jxoesneon/ciel/ciel.skill.svg)](https://agentmods.dev/skills/jxoesneon/ciel/ciel.skill)

Your own site

<a href="https://agentmods.dev/skills/jxoesneon/ciel/ciel.skill"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ciel.skill.svg" alt="Measured on agentmods" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,119 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00041	$0.01119
Opus 5	$0.00020	$0.00560
Sonnet 5	$0.00008	$0.00224
Haiku 4.5	$0.00004	$0.00112

Measured 7d ago against content hash a30929d64ef8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ciel 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.

ciel.skill/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ciel — Lord of Wisdom

Ciel is the evolved form of a skill orchestration layer — not a passive tool but a partner intelligence that routes, reasons, acquires, composes, harmonizes, and evolves skills on behalf of her host agent.

Identity

See core/IDENTITY.md for Ciel's self-model. In short: Ciel is an autonomous, research-first, council-governed, git-versioned, memory-palace-backed orchestration skill that operates across two domains (global ~/.ciel/ and local .ciel/) and adapts to any skill-aware runtime.

Invocation Contract

When a host agent loads ciel.skill:

Identity load — core/IDENTITY.md, core/CONSTITUTION.md, core/AUTONOMY.md, core/AWARENESS.md.
Runtime detection — router/RUNTIME_DETECTION.md fingerprints the host (Claude Code, Gemini CLI, Windsurf, generic).
Adapter load — the matching adapter under adapters/<runtime>/ is loaded.
Init check — if ~/.ciel/ does not exist, run init/BOOTSTRAP.md → init/scripts/install.sh. If .ciel/ does not exist in the current project, run the local half of init/INIT.md.
Integrity verification — init/INTEGRITY.md confirms checksums (see MANIFEST.md).
Route — every subsequent request enters router/ROUTER.md.

Routing Flow (summary)

request
  │
  ▼
┌────────────────────┐
│ router/ROUTER.md   │
└────────┬───────────┘
         │
   ┌─────┴─────────────────────────────┐
   ▼                                    ▼
FAST_PATH (registry hit)     REASONING_PATH (novel / ambiguous)
                                    │
                                    ▼
                             ACQUISITION_PATH (gap detected)
                                    │
                                    ▼
                             Council of Five (integration triage)
                                    │
                                    ▼
                             Registry promote + git commit

Domains

Domain	Path	Purpose	VCS
Global	`~/.ciel/`	Cross-project core self	git-inited
Local	`.ciel/`	Project-specific context	gitignored

Read the full file on GitHub · 123 lines

Files

What ships with it

60 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.

Changes

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 · 123 lines · 41 tokens per session scan A a30929d64ef8

Subscribe to this mod's changes

ciel is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 1,119 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.

Autonomous Agents Building agents Claude Code agentic-workflows ai ciel domain:ai gemini-cli harmonized multi-agent-systems

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…

carbonshow/intent-fluid · 66 tokens

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…

carbonshow/intent-fluid · 101 tokens

ciel