execute-tasks

A set of rules for deciding how coding tasks should be handled. It requires a workflow for multi-step work such as coding, debugging, planning, testing, or changes across several files.

In plain words
What is it for?
Use it before implementing features, analyzing code structures, debugging, testing, validating changes, or coordinating work across files.
Why use it?
It prevents complex tasks from starting without checking for an existing workflow session and choosing a suitable process.

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/andurilcode/accordo/execute-tasks
Clone the repo
git clone --depth 1 https://github.com/AndurilCode/accordo

Made for: Cursor.

Per session 1,528 This file is loaded in full into every session.
When invoked 1,528 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 $0.01528 $0.01528
Opus 5 $0.00764 $0.00764
Sonnet 5 $0.00306 $0.00306
Haiku 4.5 $0.00153 $0.00153

Measured yesterday against content hash 5f71ec4bea02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute-tasks 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/execute-tasks.mdc · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Execution Guidelines

🚨 MANDATORY WORKFLOW COMPLIANCE 🚨

Before starting ANY task, evaluate it using these criteria:

Use Workflow Tools When:
  • Task involves multiple steps or phases
  • Task requires coordination across multiple files
  • Task involves creating, modifying, or analyzing code structures
  • Task requires planning, analysis, or systematic approach
  • Task involves debugging, testing, or validation
  • Task creates new features, components, or systems
  • When in doubt, ALWAYS use workflows
Only Skip Workflows For:
  • Single mathematical calculations
  • One-line explanations or definitions
  • Direct copy/paste operations
  • Immediate answers to factual questions

🔍 SESSION AWARENESS & WORKFLOW DISCOVERY

⚠️ MANDATORY PRE-WORKFLOW CHECK: Before starting ANY new workflow, check for existing sessions:**

STEP 0: CHECK EXISTING SESSIONS (REQUIRED FIRST STEP)
workflow_cache_management(operation="list")

Purpose: Check for existing workflow sessions to avoid conflicts and enable session resumption Results:

  • Active Session Found & Applicable: Resume existing workflow using its session_id
  • Active Session Found & NOT Applicable: Start new workflow for current task
  • No Active Sessions: Proceed to workflow discovery
  • Multiple Sessions: Choose appropriate session, complete irrelevant ones, or start new
Session Applicability Assessment:

Before resuming any existing session, verify:

  • Is the existing workflow relevant to the current task?
  • Are you continuing the same work or starting something different?
  • If the task is different or unrelated → START NEW WORKFLOW
Session Resumption Pattern:

If existing session found AND applicable to current task, resume with:

workflow_guidance(session_id="found-session-id", action="next", context='{"choose": "current_node"}')
Session Conflict Resolution:

If multiple active sessions exist:

  1. Check session status with workflow_cache_management(operation="list")
  2. Evaluate session relevance to current task
  3. CRITICAL: Only resume if directly related to current task
  4. If unrelated: Complete or abandon existing sessions and start new workflow

Read the full file on GitHub · 170 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. yesterday First seen · 170 lines · 1,528 tokens per session scan A 5f71ec4bea02

Subscribe to this mod's changes

execute-tasks is a cursor rule published in the GitHub repository AndurilCode/accordo (5 stars, last pushed 10mo ago), licensed MIT. It adds 1,528 tokens to every session, about $0.0076 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.