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 ciel-skill-engineeringgit 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/ciel-skill-engineering)<a href="https://agentmods.dev/skills/jxoesneon/ciel/ciel-skill-engineering"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ciel-skill-engineering.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 | $0.00024 | $0.00592 |
| Opus 5 | $0.00012 | $0.00296 |
| Sonnet 5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
ciel-skill-engineering 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 4d 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.
What it actually says
CIEL ADAPTATION: Skill Engineering (The Reproduction Layer)
This skill formalizes the creation, packaging, and iteration of CIEL skills. it mandates a TDD-based documentation approach.
The Skill Lifecycle
- Initialize: Use
init_skill.cjsto generate a structured template (scripts/refs/assets). - Edit (TDD):
- RED: Identify a task where an agent fails/hallucinates without procedural guidance.
- GREEN: Write imperative instructions in
SKILL.mdto bridge that gap. - REFACTOR: Move detailed references to
references/to keep the primary skill lean.
- Package: Run
package_skill.cjsto validate YAML and ensure "No Placeholders." - Install: Deploy to
--scope workspace(repo-specific) or--scope user(global).
Design Principles
- Concise Metadata: The description MUST specify "When to use." Summary of "How" is prohibited in frontmatter.
- Progressive Disclosure: Keep
SKILL.md< 500 lines. Use linked.mdfiles for examples and deep schemas. - Degrees of Freedom: Use high-freedom (text) for heuristics; low-freedom (scripts) for fragile sequences.
Resource Bundle Patterns
- Scripts: For deterministic reliability (e.g., PDF rotation). Must output agent-friendly JSON/STDOUT.
- References: For schemas/docs that should be loaded ONLY when needed.
- Assets: Templates/Icons that are copied into the output, not read into context.
Anti-Patterns
- Placeholder Rot: Committing a skill with
// Refine implementation logic to align with Ciel 1.0 standards.or...markers. - Amnesiac Description: Describing the tool's history instead of its triggering context.
- Excessive Freedom: Using text instructions for a complex API sequence that requires a script.
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.
- 4d ago First seen · 54 lines · 24 tokens per session scan A 58d62542b21a
ciel-skill-engineering is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 592 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
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
tdd-guide
Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.
agent-tdd-london-swarm
Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm.
superpowers
Use when the user wants a disciplined software development workflow with design-first planning, implementation plans, TDD, systematic debugging, code review, or verification-before-completion, adapted from obra/superpowers.
Pair Programming
AI-assisted pair programming with multiple modes (driver$navigator$switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
V3 Security Overhaul
Complete security architecture overhaul for claude-flow v3. Addresses critical CVEs (CVE-1, CVE-2, CVE-3) and implements secure-by-default patterns. Use for security-first v3 implementation.