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.
git clone --depth 1 https://github.com/eliornl/rolemuleWrote 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/rules/eliornl/rolemule/cli)<a href="https://agentmods.dev/rules/eliornl/rolemule/cli"><img src="https://agentmods.dev/badge/rules/eliornl/rolemule/cli/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.
<a href="https://agentmods.dev/rules/eliornl/rolemule/cli"><img src="https://agentmods.dev/badge/rules/eliornl/rolemule/cli.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00912 |
| Opus 5.5 | $0.00000 | $0.00365 |
| Sonnet 5.5 | $0.00000 | $0.00182 |
| Haiku 4.5 | $0.00000 | $0.00091 |
Grade A, and why
cli 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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RoleMule CLI Conventions
Product: RoleMule CLI (rolemule entry point). Server parity via rolemule_client/ — never duplicate HTTP paths in command handlers.
Architecture
cli/ — Typer commands, formatters, config, output, pager, workflow watch
rolemule_client/ — Sync httpx client + resource modules
tests/test_cli/ — CliRunner tests (no live server in CI)
tests/test_cli_integration/ — ASGI tests (requires DATABASE_URL)
Install: bundled with make setup / make start-local / just setup (pip install -e ".[cli]" into the project venv). Tests: make cli-test.
Command patterns
- Global flags before subcommand:
rolemule --format json --no-pager workflow analyze - - HTTP only through client:
require_client(ctx)→client.<resource>.<method>() - Errors:
emit_error()oremit_workflow_error()(handlesCFG_6001,RES_3002) - Destructive ops:
require_confirm()fromcli/util.py(--confirm) - JSON payloads:
payload_from_file()/--file -for stdin - Human vs JSON:
emit(ctx, data, human=...)fromcli/output.py(pager for long human text)
Auth: JWT vs PAT
- Local JWT:
auth token set/auth token show— stored incredentials.json - PATs:
auth token create|list|revoke→/api/v1/auth/tokens(rm_pat_prefix; hash at rest);auth token create --savestores PAT incredentials.json - PAT works as
Authorization: Beareron all API + WebSocket endpoints
Adding a command
- Add method to
rolemule_client/resources/<area>.py - Expose via
@propertyonRoleMuleClientif new resource - Implement Typer command in
cli/commands/<area>.py - Add human formatter in
cli/formatters/when output is not raw JSON - Register typer in
cli/main.py - Tests:
tests/test_cli/test_<area>_client.py+test_<area>_commands.py+ matrix case - Update
docs/cli-reference.md
Security
- Credentials:
~/.rolemule/credentials.jsonmode0600 - Passwords:
getpassonly (TTY required) - Register success: never save JWT — only
verify-code/login/token set - PAT plaintext shown once on
auth token create --filepaths: read JSON only, never execute- No tokens in log output
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.
- 1mo ago First seen · 83 lines · 0 tokens per session scan A a790d799eb39
cli is a cursor rule published in the GitHub repository eliornl/rolemule (38 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 912 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.
Other cursor rules, from other repositories
development
Development environment setup and commands for backend services.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.