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/konveyor/agentic-controller/agents-mdgit clone --depth 1 https://github.com/konveyor/agentic-controllerWhat 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 | $0.01050 | $0.01050 |
| Opus 5 | $0.00525 | $0.00525 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
agentic-controller 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 yesterday.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Controller — Agent Instructions
All agent-facing guidance for this repository. Read this file first.
What this project is
A Kubernetes controller for managing AI agent workloads. Defines CRDs (Agent, AgentRun, AgentWorkflow, AgentWorkflowRun, SkillCard, SkillCollection, Gateway) and controllers for composing and executing agent workloads via Agent Sandbox.
Key documents
CONTEXT.md— Domain glossary. Canonical definitions for all project-specific terms. Consult before using any domain term.docs/adr/— Architecture Decision Records. Read before proposing changes that contradict existing decisions.
How to work in this repo
Go code
This is a controller-runtime project. Follow standard controller-runtime patterns:
- CRD types live in
api/v1alpha1/ - Controllers live in
internal/controller/ - Use
sigs.k8s.io/controller-runtimefor reconciliation - Use kubebuilder markers for CRD generation
- Run
maketo regenerate code after modifying type files
ADRs
ADRs are immutable once accepted. To change a decision, create a new ADR that supersedes the old one — don't edit the original.
Use the grill-with-docs skill when stress-testing a design decision.
It will challenge the plan against the existing domain model in
CONTEXT.md and create ADRs as decisions crystallise.
Commits
- Write concise commit messages that describe what changed and why
- One logical change per commit
- Reference issue numbers when applicable
Submitting a PR
Two repo conventions are enforced by CI (.github/workflows/pr-checks.yml)
and are easy to miss. Use the submit-pr skill for the full workflow.
1. Title prefix. Every PR title must start with an emoji alias
(use the alias, e.g. :bug:, not the character):
| Prefix | Meaning | Changelog fragment? |
|---|---|---|
:warning: |
Breaking change | required |
:sparkles: |
Non-breaking feature | required |
:bug: |
Patch / bug fix | required |
:book: |
Docs | no |
:seedling: |
Infra / tests / other | no |
:ghost: |
No release note | no |
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.
- yesterday First seen · 114 lines · 1,050 tokens per session scan A 0022450ec6dc
agentic-controller AGENTS.md is an instructions file published in the GitHub repository konveyor/agentic-controller (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,050 tokens to every session, about $0.0052 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.