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/brief-contract)<a href="https://agentmods.dev/rules/fmflurry/settings-opencode/brief-contract"><img src="https://agentmods.dev/badge/rules/fmflurry/settings-opencode/brief-contract/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/brief-contract"><img src="https://agentmods.dev/badge/rules/fmflurry/settings-opencode/brief-contract.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 | $0.00818 | $0.00818 |
| Opus 5.5 | $0.00327 | $0.00327 |
| Sonnet 5.5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
brief-contract 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 8d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brief Contract (mandatory)
Every dispatch to coder, writer, or tdd-guide MUST include a 6-field brief. Open-ended briefs cost 4.3× more tokens than precise briefs (447k vs 103k per edit). Precision gates cost savings.
Template (copy-paste verbatim)
## TASK
<one imperative sentence, one outcome>
## FILES (authoritative — this list is the scope)
- <abs/path/a.ts:120-180> — <what changes here>
Escape hatch: you may touch at most 2 files not listed. Beyond that, stop and
return `## Blocker: scope exceeds brief — <files needed and why>`.
## CHANGE
<named symbols, named target state. "Replace X with Y in Z", not "improve Z".>
## DONE-WHEN (mechanical; no judgement calls)
- `<exact command>` exits 0
## OUT OF SCOPE
- <adjacent code / files / concerns explicitly not to touch>
## CONTEXT ALREADY RESOLVED (do NOT re-derive)
- <fact> — source: codememory_retrieve "<query>" | scout manifest | prior turn
## BUDGET
edits ≤ <N> | exploratory bash ≤ <M> | turns ≤ <T>
Over budget → stop and return `## Blocker: over budget — <what remains>`.
Mandatory fields
FILES: Must list at least one file with line range. If empty or lists directories only, the brief is not dispatchable. Conductor MUST scout before dispatching.DONE-WHEN: Must contain an executable command (e.g.,npm run lintexits 0,npx tsc --noEmitexits 0). No vague criteria like "looks good" or "builds successfully"; state the exact command.
Recommended fields
TASK: One sentence, imperative voice. Outcome is the state change, not the activity.CHANGE: Named symbols, named target state. Not "improve" or "refactor" — state what replaces what.OUT OF SCOPE: Prevents scope creep. Explicitly rule out adjacent files and concerns.CONTEXT ALREADY RESOLVED: Cites the source (codememory result, scout manifest, or prior turn). Uncited assumptions = conductor must scout.
Default budgets (when unknown)
edits ≤ 5 | exploratory bash ≤ 3 | turns ≤ 25
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.
- 8d ago First seen · 69 lines · 818 tokens per session scan A 0f001e7a298b
brief-contract is a cursor rule published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 818 tokens to every session, about $0.0033 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 2026-10-08.
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.