task-summary

A response-format rule that adds a task summary and session log to coding-agent replies when session tracking is enabled in Cursor's configuration.

In plain words
What is it for?
Use it for coding, debugging, and feature work where you want implementation details, a summary, and a session log in every response.
Why use it?
It keeps a record of what the agent did and preserves a consistent response structure. It does nothing when session tracking is disabled or missing.

Cursor rule for Cursor

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/laaibaqasim/productivity-kit/task-summary
Clone the repo
git clone --depth 1 https://github.com/laaibaQasim/productivity-kit

Made for: Cursor.

Per session 488 This file is loaded in full into every session.
When invoked 488 The same file — it is already loaded in full.
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 $0.00488 $0.00488
Opus 5 $0.00244 $0.00244
Sonnet 5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 2d ago against content hash ad82d7a9b3aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-summary 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 2d 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.

.cursor/rules/task-summary.mdc · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Summary & Session Logging

Only applies when session_tracking.enabled is true in .cursor/config.json. If it is false or missing, respond normally.

If unsure, read .cursor/config.json before applying the rules below.


Requirements (when session tracking is enabled)

For every task-based response (coding, debugging, feature implementation):

  1. Always include a summary — no exceptions, regardless of response length
  2. Skip only for non-coding responses that are 2–3 lines or less
  3. For coding tasks, add an Implementation Details section before the summary listing key files changed (with line numbers where relevant)
  4. Summary heading MUST be exactly **Summary:** — hooks depend on this exact string
  5. Summary length: one paragraph maximum

Coding Task Format

[... response content ...]

**Implementation Details:**
- Updated `src/components/Button.tsx:45-60` to add loading state

**Summary:**
You asked me to [X]. I did [Y].

Session Log (every response)

Append a ### Session Log section at the end of every response. Always include it unless the user explicitly says not to.

Fields:

  • User Intent: 1–2 sentence summary of the request
  • Prompt Summary: compressed task + constraints + expected outcome
  • Provided Context: files, code, or other material the user supplied (summarize, never dump verbatim)
  • What I Did: short summary of work completed
  • Open Issues: anything unresolved, missing, or uncertain
  • Next Best Step: single most useful next action

Keep the log concise. Prefer signal over detail. No filler words.

Example

### Session Log
- **User Intent:** Add a loading state to the Button component.
- **Prompt Summary:** Update Button to show spinner and disable while loading.
- **Provided Context:** Button.tsx snippet provided.
- **What I Did:** Added `loading` prop, updated validate.ts edge case.
- **Open Issues:** No tests updated yet.
- **Next Best Step:** Add unit tests for the loading state.

Read the full file on GitHub · 63 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. 2d ago First seen · 63 lines · 488 tokens per session scan A ad82d7a9b3aa

Subscribe to this mod's changes

task-summary is a cursor rule published in the GitHub repository laaibaQasim/productivity-kit (4 stars, last pushed 4mo ago), licensed MIT. It adds 488 tokens to every session, about $0.0024 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.