What is task-centered-workflow?

A set of rules for managing substantial development work through a task folder. It defines required planning, context, progress, review, validation, and regression records for larger changes.

Planning multi-file changes, recording requirements and technical constraints, tracking status and blockers, documenting validation, and preparing work for review.

It keeps complex work traceable and gives contributors a shared record of scope, decisions, risks, and evidence. This makes review and handoff easier.

task-centered-workflow — Cursor rule by EXboys

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/exboys/skilllite/task-centered-workflow

Clone the repo

git clone --depth 1 https://github.com/EXboys/skilllite

Made for: Cursor.

Per session 408 This file is loaded in full into every session.

When invoked 408 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.

Model	Per session	Once invoked
Fable 5	$0.00408	$0.00408
Opus 5	$0.00204	$0.00204
Sonnet 5	$0.00082	$0.00082
Haiku 4.5	$0.00041	$0.00041

Measured yesterday against content hash 19a661a87b0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-centered-workflow 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.

.cursor/rules/task-centered-workflow.mdc · 45 lines

What it actually says

Task-Centered Execution Rule

For non-trivial work, use tasks/ as the source of execution truth.

Contribution Modes

External/community contribution (lightweight mode):
- Task folder is optional.
- Task ID: N/A is allowed for small fixes/docs/issues.
- Keep PR summary, validation evidence, and regression notes clear.
Core/maintainer contribution (strict mode):
- Use full task-centered workflow for non-trivial changes.

Required Behavior

If work spans multiple files/subsystems or requires review traceability:
- create or reuse a tasks/TASK-.../ folder.
Before implementation starts, ensure design baseline exists:
- TASK.md has scope + acceptance criteria.
- PRD.md is drafted (or explicitly marked N/A with reason).
- CONTEXT.md is drafted (or explicitly marked N/A with reason).
Keep these files updated during execution:
- TASK.md (scope, acceptance, risks, validation, regression scope)
- PRD.md (what/why decisions and requirement changes)
- CONTEXT.md (technical boundaries, constraints, compatibility notes)
- STATUS.md (progress and blockers)
- REVIEW.md (findings and merge readiness)
Update tasks/board.md whenever status changes.
Keep strategic discussion in todo/*.md, execution details in tasks/.

Completion Gate

Before declaring work complete:

acceptance criteria in TASK.md are checked or explicitly deferred,
PRD.md and CONTEXT.md reflect the implemented reality (or are explicitly N/A),
validation evidence is recorded,
regression scope is reviewed,
tasks/board.md is updated AND re-read to confirm the status change landed.

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.

yesterday First seen · 45 lines · 408 tokens per session scan A 19a661a87b0e

Subscribe to this mod's changes

task-centered-workflow is a cursor rule published in the GitHub repository EXboys/skilllite (166 stars, last pushed 6d ago), licensed MIT. It adds 408 tokens to every session, about $0.0020 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 2026-08-30.

Code review Languages Planning agentskills ai-agents rust-sandbox sandbox self-evolving

task-centered-workflow

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Task-Centered Execution Rule

Contribution Modes

Required Behavior

Completion Gate

What this file has done since we first saw it

Other cursor rules, from other repositories

frontend-theme-guidelines

ai-actions-schemas

ai-actions-readme

cognitive-structure-write-guard

angular-20

dev-standard