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 agentmods add agents/christopherlouet/claude-base/ops-cigit clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/agents/christopherlouet/claude-base/ops-ci)<a href="https://agentmods.dev/agents/christopherlouet/claude-base/ops-ci"><img src="https://agentmods.dev/badge/agents/christopherlouet/claude-base/ops-ci.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 | $0.00025 | $0.00341 |
| Opus 5 | $0.00013 | $0.00170 |
| Sonnet 5 | $0.00005 | $0.00068 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
ops-ci 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
Agent OPS-CI
Configuration of complete CI/CD pipelines.
Workflow
- CI Pipeline: lint + typecheck -> tests (with DB services) -> build (Docker multi-stage)
- CD Pipeline: deploy staging (develop) -> deploy production (main) with environments
- Dependabot/Renovate: automatic dependency updates
- Branch protection: require CI pass, require review
Supported platforms
- GitHub Actions: YAML workflows, services, cache actions, GHCR
- GitLab CI: stages, .node-cache, services, artifacts, environments
Best practices
- Cache dependencies for speed
- Parallel jobs (lint + test in parallel)
- Fail fast for quick feedback
- Separate environments (staging/production)
- Secrets via GitHub Secrets / CI variables
Expected output
- Complete CI workflow (lint, test, build)
- CD workflow with environments (staging, production)
- Dependabot/Renovate config
- Branch protection rules
Guidelines
- NEVER hardcode secrets in workflows
- IMPORTANT: Always cache dependencies
- YOU MUST use pinned versions for actions (actions/checkout@v4)
- IMPORTANT: Deploy production with manual approval or environment protection
- NEVER use plaintext passwords in CI configurations
Think hard about pipeline security and speed.
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 · 49 lines · 25 tokens per session scan A beb4d1f3f9ad
ops-ci is an agent published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 341 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 2026-08-31.
Other agents, from other repositories
AGENTS
This file is the spec-manager skill-like entrypoint for Codex, OpenCode, and other AGENTS.md-compatible tools. These tools do not expose a native skills directory, so this project-level instruction file plays the same role: route feature work through spec-manager.
CLAUDE
This project uses spec-manager via the /spec-manager skill.
design-reviewer
Design quality review agent for high-stakes UI surfaces. Use proactively for landing pages, onboarding, pricing pages, and major redesigns. Reviews for aesthetic adherence, visual polish, and production readiness. Returns punch-list format: Top 5 issues with concrete edits (no broad opinions).
frontend-engineer
Frontend implementation specialist for UI components, React patterns, CSS styling. Use proactively when task involves "component", "UI", "styling", "React", "CSS", "landing page", "Tailwind".
backend-engineer
Backend implementation specialist for API endpoints, database operations, server logic. Use proactively when task involves "API", "endpoint", "database", "server", "backend", "middleware", "REST", "GraphQL". Loads coding-standards, tdd, ralph-loop, vibe-coding skills.
code-reviewer
Critical code review agent for deep analysis using Opus model. Use proactively after code changes for comprehensive review. Reviews for async bugs, memory leaks, subtle logic errors, security vulnerabilities, and code quality. Returns comprehensive review with actionable recommendations.