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 rules/flomenco-inc/flo-plugin/task-intake-templategit clone --depth 1 https://github.com/Flomenco-Inc/flo-pluginWhat 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 | $0.00673 | $0.00673 |
| Opus 5 | $0.00336 | $0.00336 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
task-intake-template 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Intake Template
When the user requests a bug fix, feature, or any code change, present this intake form and ask them to fill it out (or confirm your pre-filled version) before starting implementation.
When to use
- User reports a bug ("X is broken", "Y doesn't work")
- User requests a feature ("add X to Y", "build Z")
- User asks for a code change ("update X to do Y")
- User pastes an error and asks you to fix it
When to skip
- User explicitly says "just do it" or "skip the form"
- Continuation of a task already scoped in this session
- Docs-only changes with no code impact
- User is asking a question, not requesting a change
The template
Present this and ask the user to fill in or confirm:
## Task
<one sentence: what needs to happen>
## Context
- Linear: <link or ID, if applicable>
- Design ref: <Notion page / Slack thread / screenshot / previous chat>
- Related PR: <link to existing PR, or "new">
- Branch: <existing branch to continue, or "create new">
## Acceptance Criteria (observable behaviors)
1. When I <action>, I see <result>
2. When I <action>, I see <result>
3. Edge case: when <condition>, <expected behavior>
## How You'll Verify (what you will test when I say it's done)
- <specific test step with specific user/URL/action>
- <specific test step>
## Constraints
- <anything unusual: scope limits, files not to touch, users to test with>
## Known State
- Current behavior: <what's happening now, including exact errors>
- Already tried: <what was attempted that didn't work>
How to use it
If the user gives enough detail
Pre-fill the template from their message, then ask:
"Here's how I understand the task — please confirm or correct before I start: [pre-filled template]"
If the user's request is vague
Ask them to fill in the critical fields:
"Before I start, I need a few things to avoid wasted rounds:
- Acceptance criteria — what specifically should I see when this is working?
- Known state — what's the current behavior / exact error?
- How you'll verify — what will you test?"
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 · 81 lines · 673 tokens per session scan A 536c14a2c9a5
task-intake-template is a cursor rule published in the GitHub repository Flomenco-Inc/flo-plugin (0 stars, last pushed 2d ago), licensed MIT. It adds 673 tokens to every session, about $0.0034 per session on Opus 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 2026-08-31.
Other cursor rules, from other repositories
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.
cli-error-handling
CLI command error handling patterns.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.