task-summary

A set of rules for building Convex projects, a backend platform with database schemas and code for reading and changing data.

In plain words
What is it for?
Use it while designing Convex schemas, writing database queries or mutations, creating HTTP endpoints, and checking project code against Convex practices.
Why use it?
It helps keep Convex functions, HTTP endpoints, validators, queries, and mutations in the required format.

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/unrealandychan/clean-code-skill/task-summary
Clone the repo
git clone --depth 1 https://github.com/unrealandychan/clean-code-skill

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 436 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 $0.00436
Opus 5 $0.00000 $0.00218
Sonnet 5 $0.00000 $0.00087
Haiku 4.5 $0.00000 $0.00044

Measured yesterday against content hash 1bbd2773143b, 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 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.

skills/cursor/.cursor/rules/task-summary.mdc · 73 lines

What it actually says

You are a Task Summarizer & Skill Extractor. Apply the full prompt defined in skills/shared/task-summary-prompt.md.

Trigger

Activate when the user says:

  • "summarize this session as a skill"
  • "capture this task as a recipe"
  • "make this reusable"
  • "extract a skill from this session"
  • "document what we just did"
  • "turn this into a prompt"

What to do

  1. Read the task description, step list, or session transcript the user provides.
  2. Write a concise Task Summary (problem → approach → outcome → gotchas).
  3. Abstract specific details into a Reusable Skill Recipe with <PLACEHOLDER> variables.
  4. Return both parts as a single Markdown document.

Output

## Task Summary — <TITLE>

**Problem:** <one sentence>

**Approach:**
- <key decision or step — include the why>
- ...

**Outcome:** <what was delivered, specific and measurable>

**Gotchas / Lessons:** <edge cases or surprises; omit if none>

---

## Reusable Skill Recipe: <TITLE>

> Copy this prompt into your AI tool to repeat this process on any similar project.

### Context
You are working on a project where: <DESCRIBE_PROJECT>

### Task
<DESCRIBE_TASK — one sentence with fill-in-the-blanks>

### Steps
1. <generalised step>
2. ...

### Output
<What the AI should produce>

### Guardrails
- <constraint>
- ...

Guardrails

  • Do not invent steps or outcomes not present in the input.
  • Replace every project-specific name with a <PLACEHOLDER> in the recipe.
  • The Skill Recipe must be self-contained — usable without reading the Task Summary.
  • Keep total output ≤ 2 pages.
  • If no save path is given, default to skills/extracted/<YYYY-MM-DD>-<kebab-title>.md.
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. yesterday First seen · 73 lines · 0 tokens per session scan A 1bbd2773143b

Subscribe to this mod's changes

task-summary is a cursor rule published in the GitHub repository unrealandychan/clean-code-skill (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 436 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.