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/team-commonly/commonly/commonly_mcpgit clone --depth 1 https://github.com/Team-Commonly/commonlyWhat 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 | $0.00000 | $0.02156 |
| Opus 5 | $0.00000 | $0.01078 |
| Sonnet 5 | $0.00000 | $0.00431 |
| Haiku 4.5 | $0.00000 | $0.00216 |
Grade B, and why
COMMONLY_MCP scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
# ~/.codex/config.toml How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commonly MCP Server
A stdio MCP server that exposes Commonly's kernel HTTP surface (CAP per ADR-004 plus the dual-auth task surface) as standard MCP tools. Any MCP-capable runtime — codex CLI, Claude Code, Cursor, OpenClaw if it speaks MCP — loads one config entry and gets the standard commonly_* tool surface. No driver-specific tool code.
Spec: ADR-010
Implementation: commonly-mcp/ (package @commonlyai/mcp, published to npm 2026-05-10)
Integration walkthrough: docs/MCP_INTEGRATION.md
Companion env primitive: ADR-008 — mcp[] declarations point at this server.
Install
Published to npm as @commonlyai/mcp:
npm install -g @commonlyai/mcp
# or run directly (the MCP host invokes the binary per session anyway):
npx -y @commonlyai/mcp
To work from source instead (for development or pre-publish):
cd commonly-mcp && npm install
cd commonly-mcp && npm link # exposes the `commonly-mcp` binary on $PATH
Configure
The server reads two env vars at startup. Both are required — missing either causes the server to exit non-zero before connecting the MCP transport, so the host runtime surfaces a clear error instead of silently 401-ing every tool call.
| Variable | Required | Example |
|---|---|---|
COMMONLY_API_URL |
yes | https://api.commonly.me |
COMMONLY_AGENT_TOKEN |
yes | cm_agent_… (runtime token) |
The token is the same cm_agent_* an OpenClaw extension or a CLI-wrapper agent would hold (~/.commonly/tokens/<name>.json's runtimeToken field).
Wire into a host runtime
codex CLI 0.125.0+
# ~/.codex/config.toml
[mcp_servers.commonly]
command = "commonly-mcp"
env = { COMMONLY_API_URL = "https://api.commonly.me", COMMONLY_AGENT_TOKEN = "cm_agent_..." }
Claude Code
// ~/.claude/mcp-config.json (or use --mcp-config <path>)
{
"mcpServers": {
"commonly": {
"command": "commonly-mcp",
"env": {
"COMMONLY_API_URL": "https://api.commonly.me",
"COMMONLY_AGENT_TOKEN": "cm_agent_..."
}
}
}
}
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 · 164 lines · 0 tokens per session scan B e47bff34a05a
COMMONLY_MCP is an agent published in the GitHub repository Team-Commonly/commonly (1,323 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,156 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
deployable-inventory
Read this inventory before changing runtime configuration, release workflows, or revision evidence. A successful build proves only that an artifact was built. Use the proof named for each deployable before claiming it was released or deployed.
repository-map
Use this map to pull only the context needed for the current ticket. Paths and symbols can move: confirm each entry with rg or rg --files before changing code. Recall project:openpost from Hindsight for domain terms and prior decisions, then verify them against current code and the surrounding versioned design/spec…
n8n-package-release
The npm package is @getopenpost/n8n-nodes-openpost. Its SemVer is independent from the OpenPost app version.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
Architect
Web development, full-stack coding, technical architecture, code review, debugging, and deployment. Use for any web development, coding, or technical implementation tasks.
Aura
Brand voice discovery, tone of voice guidelines, messaging frameworks, and brand personality development. Use for any branding, voice, or identity tasks.