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 product-capabilitygit 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/product-capability)<a href="https://agentmods.dev/skills/jxoesneon/ciel/product-capability"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/product-capability/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/product-capability"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/product-capability.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 | $0.00019 | $0.00525 |
| Opus 5 | $0.00010 | $0.00262 |
| Sonnet 5 | $0.00004 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
product-capability 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.
What it actually says
CIEL ADAPTATION: Product Capability (The Engineering Contract)
This skill bridges the gap between "What should we build?" and "How exactly must it behave?". It turns product intent into a durable engineering contract.
The Capability Manifest
For every major feature, the Orchestrator MUST produce a CAPABILITY.md (or update PRODUCT.md) specifying:
1. Invariants & Business Rules
Fixed rules that MUST hold true regardless of implementation (e.g., "A user cannot have more than 5 active sessions").
2. Trust Boundaries & Policy
Explicitly define where data ownership shifts and where security gates are enforced.
3. States & Transitions
Map the required lifecycle of the data/feature (e.g., Draft -> Pending -> Published).
4. Non-Goals
Hard boundaries on what the capability does NOT own to prevent scope drift.
Non-Negotiable Rules
- Explicit Blocker Detection: If the product intent conflicts with existing repo constraints, halt and escalate.
- Durable Artifact: The resulting document must be reusable across different agent sessions (e.g., stored in
docs/capabilities/). - No Guessing: Mark unresolved product questions as
OPEN_QUESTIONSand do not plan until they are resolved.
Anti-Patterns
- Vague Planning Prose: Writing 5 paragraphs of "how it will work" without defining a single state transition or invariant.
- Implicit Assumptions: Assuming the developer "knows" that a certain field is mandatory without documenting it in the contract.
- Smoothing Over Conflicts: Attempting to code around a fundamental product contradiction.
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 · 58 lines · 19 tokens per session scan A a83a31dfb0ff
product-capability is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 19 tokens to every session and 525 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.
lov-public-security-filing
A guided workflow for applying for Chinese public-security internet filing after a website has passed ICP filing and is publicly accessible in mainland China. ICP filing is the earlier Chinese registration required for many mainland websites; public-security filing is a separate police-record process.
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.
Code Quality Review
Conduct a comprehensive code quality review focused on clean code, architecture, and project standards.