skills: Instructions file for Codex

AGENTS.md

skills AGENTS.md is an instructions file for Codex, OpenCode from camunda/skills. It costs 1,830 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Camunda skills, a toolkit for developing and operating Camunda process automation. They explain available skills such as BPMN workflows, FEEL expressions, DMN decisions, forms, and connectors.

In plain words
What is it for?
Use them when building or operating Camunda 8.8+ processes, configuring c8ctl, or creating BPMN, FEEL, DMN, forms, and connector definitions.
Why use it?
They help an agent choose the right Camunda tool and follow the project's setup and documentation rules.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is camunda/skills's own configuration. It tells Codex and OpenCode how to work on skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to camunda/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/camunda/skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/camunda/skills

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/camunda/skills/agents-md/github.svg)](https://agentmods.dev/instructions/camunda/skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/camunda/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/camunda/skills/agents-md/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.

agentmods 80×15 button for skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/camunda/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/camunda/skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,830 This file is loaded in full into every session.
When invoked 1,830 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01830 $0.01830
Opus 5.5 $0.00732 $0.00732
Sonnet 5.5 $0.00366 $0.00366
Haiku 4.5 $0.00183 $0.00183

Measured 2mo ago against content hash 72ff4c63eb06, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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.

AGENTS.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Camunda Skills

AI skills for Camunda 8.8+ development. Use these skills to create, deploy, and operate Camunda process automation solutions.

Available Skills

Skill Use When
camunda-c8ctl Installing and configuring c8ctl, picking/setting up a cluster (incl. local c8run), managing profiles, plugins
camunda-docs Verifying a Camunda 8 technical fact against the official docs (FEEL signatures, BPMN extension shapes, API endpoints, version requirements) before writing it down
camunda-bpmn Creating or editing BPMN 2.0 processes (elements, flows, gateways, events, subprocesses)
camunda-feel Writing FEEL expressions (gateway conditions, input/output mappings, timer definitions)
camunda-dmn Authoring DMN decisions for business-rule tasks — decision tables (UNIQUE/ANY/FIRST/RULE ORDER/COLLECT), literal expressions, DRG linking, structural validation via npx dmnlint
camunda-forms Creating Camunda Form JSON schemas for user tasks
camunda-connectors Configuring pre-built connectors (REST, Slack, Kafka, etc.) via element templates
camunda-development Choosing between OOTB connectors, custom connector templates, custom Java connectors, and job workers before writing integration code
camunda-job-workers Implementing custom Camunda 8 job workers in Java, Camunda Spring Boot, or TypeScript — handler code that activates jobs and signals complete / fail / BPMN error
camunda-connectors-development Building custom Camunda 8 connectors — JSON-only template on a protocol connector (Path A) or custom Java connector via the Connectors SDK (Path B, outbound + inbound)
camunda-process-mgmt Deploying resources, starting/inspecting instances, resolving incidents, completing user tasks — all via c8ctl
camunda-process-test Authoring and running Camunda Process Test (CPT) suites that reach 100% BPMN coverage with segment-based scenarios — .test.json instructions, mvn test, coverage report parsing
camunda-ai-agents Building AI agents in BPMN — AI Agent connector on an ad-hoc subprocess, tool modeling, fromAi() parameters, prompts, sub-flow tools

Read the full file on GitHub · 71 lines

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.

  1. 2mo ago First seen · 71 lines · 1,830 tokens per session scan A 72ff4c63eb06

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository camunda/skills (26 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,830 tokens to every session, about $0.0073 per session on Opus 5.5. 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.

Related

skills AGENTS.md compared with instructions from other repositories

skills AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skills AGENTS.mdcamunda/skillsInstructions file264d agoApache-2.0A1,830Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot