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 automation-audit-opsgit 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/automation-audit-ops)<a href="https://agentmods.dev/skills/jxoesneon/ciel/automation-audit-ops"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/automation-audit-ops/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/automation-audit-ops"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/automation-audit-ops.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 | $0.00025 | $0.00625 |
| Opus 5 | $0.00013 | $0.00313 |
| Sonnet 5 | $0.00005 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
automation-audit-ops 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIEL ADAPTATION: Automation Audit Ops (Inventory & Rationalization)
This skill dictates how the Orchestrator inventories and rationalizes workspace automations (CI jobs, hooks, connectors, MCP servers). It focuses on evidence-backed classification to drive "Keep / Merge / Cut / Fix-Next" decisions.
The Audit Workflow
1. Evidence-First Inventory
The Orchestrator MUST NOT assume state from configuration files. It MUST verify truth by:
- Inspecting active Git hooks (
.git/hooks). - Checking live GitHub Action run histories.
- Probing MCP server connectivity.
- Verifying authentication tokens for connectors.
2. State Classification
Every identified automation MUST be classified into one of these states:
- Active: Configured, authenticated, and recently verified as passing.
- Degraded: Configured but failing (broken code or transient error).
- Stale: Authenticated but no longer producing useful output.
- Broken: Authentication expired or configuration invalid.
- Redundant: Overlaps significantly with another active automation.
3. The Rationalization Matrix
For every degraded, stale, or redundant automation, the Orchestrator MUST produce a recommendation:
- Keep: The automation is vital and functional.
- Merge: Consolidate overlapping surfaces into a single canonical lane.
- Cut: Delete stale or entirely redundant automations.
- Fix-Next: Prioritize immediate repair of a high-signal broken path.
Integration Context
- Workspace Audit: Uses
workspace-surface-auditas the primary discovery tool. - Verification: Uses the
verification-loopto confirm the state of "Fix-Next" items. - Knowledge: Records the final inventory in the MemPalace Knowledge Graph for future reference.
Anti-Patterns
- Theorizing: Claiming a tool is working based on its documentation without checking live logs.
- Fix-First: Attempting to repair automations before completing the global inventory and rationalization.
- Silent Redundancy: Allowing multiple overlapping automations to run, creating noise and conflicting state 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 · 68 lines · 25 tokens per session scan A fec81b544345
automation-audit-ops is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 25 tokens to every session and 625 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-npm-publisher
An npm package publishing workflow that sets up releases through GitHub Actions using OIDC, a login-free trust method, or a local granular NPM token. It covers initial setup, publishing, audit checks, and verifying the package on the npm registry.
gh-ci-analyzer
A guide for using GitHub’s command-line tool to investigate failed GitHub Actions runs. GitHub Actions is GitHub’s system for automatically building, testing, and deploying code.
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
bash-scripting
Bash scripting workflow for creating production-ready shell scripts with defensive patterns, error handling, and testing.
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.