generate_tasks_tracer

generate_tasks_tracer is a cursor rule for coding agents from markhazlett/cursor-rules. It costs 0 tokens per session (790 once invoked), scanned A, original, Apache-2.0.

A task-list generator that turns a product requirements document (PRD) into Markdown tasks for building a small, end-to-end first version of a feature. This first version proves the main architecture and user flow before adding polish or edge-case handling.

In plain words
What is it for?
Use it to analyze a PRD and create parent tasks for a tracer-bullet implementation in `/tasks/`. It helps organize the files, endpoints, and interface needed for the feature’s main path.
Why use it?
It gives a team a concrete starting plan and quick feedback on whether the proposed design works. It avoids committing to a full implementation before the basic flow is proven.

Cursor rule

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.

agentmods
npx agentmods add rules/markhazlett/cursor-rules/generate_tasks_tracer
Clone the repo
git clone --depth 1 https://github.com/markhazlett/cursor-rules
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 790 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00790
Opus 5 $0.00000 $0.00395
Sonnet 5 $0.00000 $0.00158
Haiku 4.5 $0.00000 $0.00079

Measured 3d ago against content hash e0310e69c87a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

rules/generate_tasks_tracer.mdc · 94 lines

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

  1. Receive PRD Reference
    User tells the AI which PRD file to use.

  2. Analyze PRD
    Read functional requirements, user stories, constraints, etc.

  3. Phase TB – Generate Tracer-Bullet Parent Tasks
    Goal: deliver the thin, working slice described above.
    Action: Create ~3-5 high-level tasks prefixed TB-.
    Pause: Output them and say:

    “Tracer-bullet tasks ready. Reply Go TB to break these into sub-tasks.”

  4. Wait for “Go TB”

  5. Phase TB – Generate Tracer-Bullet Sub-Tasks
    Expand each TB-x parent into actionable TB-x.y sub-tasks.
    Update Relevant Files to cover only the tracer-bullet slice.

  6. Validation Checkpoint
    Conclude Phase TB with:

    “Tracer-bullet sub-tasks generated. After this slice is validated, reply Go PR to plan hardening & enhancements.”

  7. Wait for “Go PR”

  8. Phase PR – Generate Production-Readiness Parent Tasks
    Add ~3-5 high-level tasks prefixed PR- (tests, security, perf, UX polish, edge-cases).
    Present them and pause:

    “Production-readiness tasks ready. Reply Go PR Sub to break these down.”

Read the full file on GitHub · 94 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. 3d ago First seen · 94 lines · 0 tokens per session scan A e0310e69c87a

Subscribe to this mod's changes

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.