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 instructions/fluxcd/agent-skills/agents-mdgit clone --depth 1 https://github.com/fluxcd/agent-skillsWrote 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/instructions/fluxcd/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/fluxcd/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/fluxcd/agent-skills/agents-md.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 | $0.00809 | $0.00809 |
| Opus 5 | $0.00404 | $0.00404 |
| Sonnet 5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
agent-skills AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This repository contains AI agent skills for Flux CD, Kubernetes, and GitOps. Skills follow the Agent Skills Open Standard.
Repository Layout
skills/{skill-name}/
├── SKILL.md # Agent instructions (frontmatter + workflow)
├── scripts/ # Helper scripts (thin bash wrappers around flux/flux-schema)
├── references/ # On-demand reference docs (checklists, API summaries)
├── assets/schemas/ # Bundled OpenAPI schemas for Flux CRDs
└── evals/evals.json # Evaluation scenarios with expected behavior
tests/{skill-name}/ # Test fixtures for offline evaluation
.claude-plugin/marketplace.json # Skill registry for distribution
Makefile # Schema downloads and test targets
skills/gitops-repo-audit/scripts/validate.shis vendored from the flux-schema action (the single source of truth). Don't edit it here — runmake sync-validateto refresh it, and send changes upstream.
Working on Existing Skills
- Read the skill's
SKILL.mdto understand its workflow and allowed tools - Read all files in
references/andscripts/before making changes - Keep
SKILL.mdunder ~15KB — heavy reference material belongs inreferences/
Running Skill Evals
Each skill has an evals/evals.json file with evaluation scenarios. When asked to run them:
- Read
evals/evals.jsonto get the list of eval prompts and their expectations - For each eval, spawn a sub-agent with this prompt template:
You are a [skill role]. load the skill from `skills/{skill-name}/SKILL.md` exactly — read it first, then follow the workflow phases. Your task: [eval prompt from evals.json] Important: - Do not seach the web, use only the skill references and your own reasoning - Produce the full structured report as specified in the workflow if there is one - Score each eval output against the
expectationsarray — each expectation is a pass/fail check - Report results as a scorecard: eval id, pass/fail counts, and any missed expectations
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 · 69 lines · 809 tokens per session scan A bcb3f5d7ea99
agent-skills AGENTS.md is an instructions file published in the GitHub repository fluxcd/agent-skills (216 stars, last pushed 3d ago), licensed Apache-2.0. It adds 809 tokens to every session, about $0.0040 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 2026-08-30.
Other instructions, from other repositories
flux-operator AGENTS.md
AGENTS.md instructions for controlplaneio-fluxcd/flux-operator, covering agents instructions, project overview, repository structure, rules of engagement for ai agents and development commands for ai agents.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
superpowers-reasonix AGENTS.md
Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.
ai-mind AGENTS.md
AGENTS.md instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
vvvv-skills CLAUDE.md
Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.
pi AGENTS.md
AGENTS.md instructions for counterposition/pi, covering agents.md, commands, pattern: pnpm --filter @counterposition/pi-web-search run, single test file and single test by name.