agents

A command that displays a capability manifest for supported AI coding agents. It shows installation locations, support levels, configuration support, instruction formats, and documentation details.

In plain words
What is it for?
Use it to inspect agent support in a readable table or retrieve the same information as JSON.
Why use it?
It gives developers one place to check which agents are supported and how each one is configured.

Command

Install

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.

agentmods
npx agentmods add commands/rolecraft-sh/rolecraft/agents
Clone the repo
git clone --depth 1 https://github.com/rolecraft-sh/rolecraft
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 821 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00821
Opus 5 $0.00000 $0.00411
Sonnet 5 $0.00000 $0.00164
Haiku 4.5 $0.00000 $0.00082

Measured 3d ago against content hash 0ad4321cb3cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents 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 3d 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.

docs/commands/agents.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rolecraft agents

Display the agent capability manifest — a structured overview of all supported AI coding agents, their skill install directories, support levels, and MCP server configuration support.

Usage

rolecraft agents

# Output as JSON
rolecraft agents --json

Description

The agents command reads the agent capability manifest — a single source of truth for agent support metadata — and displays it in a human-readable table or machine-readable JSON.

Each agent entry includes:

Field Description
flag CLI flag used with install (e.g. --claude, --cursor)
name Agent identifier
skillInstallScope Where skills are installed (global path or project path)
supportLevel verified, community, legacy, or experimental
mcpSupport Whether MCP servers are supported and in which config format
instructionFormat Skill instruction file format (skill-md, mdc, agents-md, etc.)
docUrl Official documentation URL
lastVerified Last verification date (ISO date)

Support levels

Level Meaning
verified Actively tested and maintained by the RoleCraft team
community Community-contributed; maintained on best-effort basis
legacy Previous generation agent; no active development
experimental Known to exist; not formally tested

Example output

$ rolecraft agents

🔍 Agent Capability Manifest

Total agents: 87

## VERIFIED

| Agent | Skill Scope | MCP | Instruction | Docs |
|-------|-------------|-----|-------------|------|
| opencode | ~/.agents/skills/ | ❌ | skill-md | [docs](https://opencode.ai) |
| claude-code | ~/.claude/skills/ | ✅ | skill-md | [docs](https://docs.anthropic.com/en/docs/claude-code) |
| cursor | ~/.cursor/skills/ | ✅ | skill-md | [docs](https://cursor.com) |
| windsurf | ~/.codeium/windsurf/skills/ | ✅ | skill-md | [docs](https://docs.windsurf.com) |
| devin | ./.devin/skills/ | ❌ | skill-md | [docs](https://devin.ai) |
| ... | ... | ... | ... | ... |

## MCP-Supported Agents

These agents have built-in MCP configuration support:
  • claude-code (mcpServers)
  • cursor (mcpServers)
  • windsurf (mcpServers)
  • continue (experimental.mcpServers)

## Validation

Manifest valid: ✅ Yes
Agent count: 87

Read the full file on GitHub · 105 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. 3d ago First seen · 105 lines · 0 tokens per session scan A 0ad4321cb3cf

Subscribe to this mod's changes

agents is a command published in the GitHub repository rolecraft-sh/rolecraft (75 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 821 tokens. 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.