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/markhazlett/cursor-rulesWrote 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/markhazlett/cursor-rules/generate_tasks_tracer)<a href="https://agentmods.dev/rules/markhazlett/cursor-rules/generate_tasks_tracer"><img src="https://agentmods.dev/badge/rules/markhazlett/cursor-rules/generate_tasks_tracer/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/markhazlett/cursor-rules/generate_tasks_tracer"><img src="https://agentmods.dev/badge/rules/markhazlett/cursor-rules/generate_tasks_tracer.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 | $0.00790 |
| Opus 5.5 | $0.00000 | $0.00316 |
| Sonnet 5.5 | $0.00000 | $0.00158 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
generate_tasks_tracer 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Rules Task List Generator (Tracer-Bullet Edition)
Format & Location
- Format: Markdown (
.md) - Directory:
/tasks/ - Filename:
tasks-[prd-file-name].md(e.g.,tasks-prd-user-profile-editing.md)
Tracer-Bullet Primer 🔍💡
A tracer bullet is a slim, end-to-end slice of the feature that proves the architecture, wiring, and basic happy path without worrying (yet) about robustness, polish, or edge-cases.
Think of it as:
| Principle | What it means in practice |
|---|---|
| Visible Path | Users (or stakeholders) can click through the entire flow at least once. |
| Minimal Surface Area | Only the files, endpoints, and UI needed for that single flow are touched. |
| Rapid Feedback | Because it ships fast, we can validate the direction before committing to full-scale work. |
| Foundation First | Once the slice works, we harden, extend tests, add error handling, and layer on enhancements. |
Process
-
Receive PRD Reference
User tells the AI which PRD file to use. -
Analyze PRD
Read functional requirements, user stories, constraints, etc. -
Phase TB – Generate Tracer-Bullet Parent Tasks
Goal: deliver the thin, working slice described above.
Action: Create ~3-5 high-level tasks prefixedTB-.
Pause: Output them and say:“Tracer-bullet tasks ready. Reply Go TB to break these into sub-tasks.”
-
Wait for “Go TB”
-
Phase TB – Generate Tracer-Bullet Sub-Tasks
Expand eachTB-xparent into actionableTB-x.ysub-tasks.
Update Relevant Files to cover only the tracer-bullet slice. -
Validation Checkpoint
Conclude Phase TB with:“Tracer-bullet sub-tasks generated. After this slice is validated, reply Go PR to plan hardening & enhancements.”
-
Wait for “Go PR”
-
Phase PR – Generate Production-Readiness Parent Tasks
Add ~3-5 high-level tasks prefixedPR-(tests, security, perf, UX polish, edge-cases).
Present them and pause:“Production-readiness tasks ready. Reply Go PR Sub to break these down.”
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 · 94 lines · 0 tokens per session scan A e0310e69c87a
generate_tasks_tracer is a cursor rule published in the GitHub repository markhazlett/cursor-rules (2 stars, last pushed 1y ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 790 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 2026-08-31.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).