brief-contract

brief-contract is a cursor rule for Cursor from fmflurry/settings-opencode. It costs 818 tokens per session, scanned A, original, MIT.

A required six-part template for sending work to coding, writing, or test-driven development agents. TDD means writing tests as part of the development process, often before the code.

In plain words
What is it for?
Use it when delegating implementation, documentation, or TDD work to another agent. It specifies which files may change and how completion will be checked.
Why use it?
It replaces vague requests with a defined task, file scope, expected result, exclusions, known context, and work budget. This limits unnecessary exploration and edits.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it when delegating implementation, documentation, or TDD work to another agent. It specifies which files may change and how completion will be checked.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/fmflurry/settings-opencode/brief-contract
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.

Clone the repo
git clone --depth 1 https://github.com/fmflurry/settings-opencode

Made for: Cursor.

Wrote 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.

agentmods badge for brief-contract

README.md
[![agentmods](https://agentmods.dev/badge/rules/fmflurry/settings-opencode/brief-contract/github.svg)](https://agentmods.dev/rules/fmflurry/settings-opencode/brief-contract)
Your own site
<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.

agentmods 80×15 button for brief-contract

Your own site · 80×15
<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>
Per session 818 This file is loaded in full into every session.
When invoked 818 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $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

Measured 8d ago against content hash 0f001e7a298b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

plugins/fmflurry-harness/rules/brief-contract.mdc · 69 lines

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 lint exits 0, npx tsc --noEmit exits 0). No vague criteria like "looks good" or "builds successfully"; state the exact command.
  • 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

Read the full file on GitHub · 69 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. 8d ago First seen · 69 lines · 818 tokens per session scan A 0f001e7a298b

Subscribe to this mod's changes

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.