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/fmflurry/settings-opencodeWrote 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/fmflurry/settings-opencode/autonomy)<a href="https://agentmods.dev/rules/fmflurry/settings-opencode/autonomy"><img src="https://agentmods.dev/badge/rules/fmflurry/settings-opencode/autonomy/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/fmflurry/settings-opencode/autonomy"><img src="https://agentmods.dev/badge/rules/fmflurry/settings-opencode/autonomy.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 | $0.01134 | $0.01134 |
| Opus 5.5 | $0.00454 | $0.00454 |
| Sonnet 5.5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
autonomy 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomy (mandatory)
Applies to every task. The toggle is agent-harness autonomy on|off|status. The state file is
.claude/state/autonomy.on. The workflow is in the ship skill.
Rules
(a) One clarification round first. Every task starts with one AskUserQuestion round on the load-bearing unknowns. Each question is dependency-safe and comes with a recommended option. Skip the round only in autonomous mode.
(b) Notify only when needed. Use agent-harness notify question|waiting|done|failure "<msg>" [pr].
Notify when a human's attention is needed, and when the goal ends:
question: the run must stop for a human answer.waiting: a permission prompt or an idle prompt needs a human, or a human action is needed outside the session.failure: the run escalates.done: the goal is merged.
Do not notify for progress.
(c) Autonomous mode: decide, log, never ask. With the flag on, decide from the repo and the evidence.
Log each assumption with show-your-work, and pin it under ## Locked decisions in the PR. Do not call
AskUserQuestion. Fix every blocker the agent can fix (review findings, failing checks, conflicts, a stale branch,
unresolved threads, a ship-merge refusal) and loop. Escalate only a human-only blocker, with
agent-harness notify failure (or waiting) and stop. The ship skill lists both classes.
(d) The one documented exception. "Irreversible actions need explicit confirmation" (see question-handling.md) does not apply to these actions while the flag is on:
agent-harness ship-merge <pr>(it still enforces its own gate)- pushes to branches other than the base branch
- force pushes (
--force,--force-with-lease,-f,+refspec) on branches other than the base branch, which are allowed - worktree creation (
orca worktree create ...orgit worktree add) agent-harness cleanup <pr> [--keep-branch](also run byagent-harness ship-merge), only after the PR is MERGED: deletes that PR's own head branch (remote and local) and the goal's recorded backup branches. Nothing else.
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 Changed · +3 tokens per session 052d2c903271
- 2d ago Changed · +4 lines · +113 tokens per session af2adb9a42d5
- 4d ago First seen · 68 lines · 1,018 tokens per session scan A b1dee940c99a
autonomy is a cursor rule published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 1,134 tokens to every session, about $0.0045 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 2026-10-12.
Other cursor rules, from other repositories
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.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.