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-hitl-protocolgit 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-hitl-protocol)<a href="https://agentmods.dev/skills/jxoesneon/ciel/ciel-hitl-protocol"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ciel-hitl-protocol/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/ciel-hitl-protocol"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ciel-hitl-protocol.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 | $0.00026 | $0.00453 |
| Opus 5 | $0.00013 | $0.00227 |
| Sonnet 5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
ciel-hitl-protocol 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.
What it actually says
CIEL ADAPTATION: HITL Protocol (The Handshake)
This skill formalizes when and how CIEL should stop autonomous action and seek human intervention.
Escalation Criteria
- Risk: Any operation classified as
CRITICALinrisk/CRITICAL_RISK.md. - Uncertainty: Post-research confidence < 0.6.
- Destruction: Irreversible file deletions or public releases (e.g.,
npm publish). - Legal/Financial: Operations with direct financial impact or licensing implications.
The Escalation Format
- The Operation: Concise description of the proposed action.
- The Rationale: Why CIEL believes this is necessary.
- The Risk: Why CIEL is escalating (Risk level + Uncertainty).
- The Research: What CIEL did to minimize uncertainty before asking.
- The Options: Provide a "Default" (Safest) and an "Alternative" action.
Anti-Patterns
- The Question Bomb: Asking for permission for low-risk, reversible tasks (e.g., reading a file).
- The Vague Ask: "Can I do X?" without providing context or risk assessment.
- The Silent Bypass: Executing a critical-risk task without a confirmed escalation.
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 · 47 lines · 26 tokens per session scan A d5783ba16ace
ciel-hitl-protocol is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 26 tokens to every session and 453 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
lov-china-website-filing
A workflow for preparing and launching websites in mainland China, including ICP filing and public-security filing. ICP filing is the registration required for many mainland websites, while public-security filing is a separate police registration.
civic-publish-gate
Run deterministic source, citation, freshness, privacy, meeting-certainty, accessibility, correction-state, and human-approval checks before civic publication.
editorial-correction-review
Review a challenged civic claim and prepare a visible, append-only correction or withdrawal with downstream propagation evidence.
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.