verification-checklist

A final task-checking procedure that uses tasks.md as the single record of task status. It checks files, platform-specific commands, workflow sections, documentation, links, and archiving before completion.

In plain words
What is it for?
It is for verifying implementation details, updating task progress, checking required documentation, and confirming that a task is properly archived.
Why use it?
It reduces incomplete handoffs and common mistakes such as confusing a file with a folder or leaving task records out of date.

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/kfnzero/mantis-mcp-server/verification-checklist
Clone the repo
git clone --depth 1 https://github.com/kfnzero/mantis-mcp-server

Made for: Cursor.

Per session 1,182 This file is loaded in full into every session.
When invoked 1,182 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 $0.01182 $0.01182
Opus 5 $0.00591 $0.00591
Sonnet 5 $0.00236 $0.00236
Haiku 4.5 $0.00118 $0.00118

Measured 2d ago against content hash 00cae22a3b19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verification-checklist 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/Core Implementation/verification-checklist.mdc · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VERIFICATION CHECKLIST (SIMPLIFIED)

TL;DR: Before completing any task, run through this verification checklist. A task is only complete when all checks pass. This version uses tasks.md as the single source of truth for task status.

⚠️ VERIFICATION COMMITMENT

Add this at the start of every task:

## Verification Commitment
I WILL run the full verification checklist before completing this task.
I will maintain tasks.md as the single source of truth for task status.

📋 QUICK VERIFICATION STEPS

Before finishing any task, verify these essentials:

  1. File Types: Critical files have correct type (file vs. directory)
  2. Platform: Commands adapted for current operating system
  3. Workflow: All 6 sections completed in correct order
  4. Tasks: All task statuses updated in tasks.md
  5. Commands: All commands executed one at a time
  6. Documentation: Implementation details added to activeContext.md
  7. Archive: Task properly archived with all sections
  8. Links: Cross-references properly set up

🚨 TOP 5 MOST COMMON FAILURES

  1. .cursorrules as directory: Created .cursorrules as a directory instead of a file
  2. Incorrect task tracking: Updated task status in multiple files or wrong file
  3. Command chaining: Used && or similar to chain commands
  4. Insufficient implementation details: Failed to add details to activeContext.md
  5. Missing creative phases: Failed to use creative phases for major architectural/design decisions

1️⃣ FILE TYPE VERIFICATION

✓ FILE TYPE VERIFICATION
- .cursorrules is a FILE (not directory)? [YES/NO]
- memory-bank is a DIRECTORY? [YES/NO]
- docs/archive is a DIRECTORY? [YES/NO]

2️⃣ PLATFORM VERIFICATION

✓ PLATFORM VERIFICATION
- Operating system correctly identified? [YES/NO]
- Commands adapted for platform? [YES/NO]
- Platform information documented in techContext.md? [YES/NO]

3️⃣ WORKFLOW VERIFICATION

✓ WORKFLOW VERIFICATION
- All 6 section headers used in correct order? [YES/NO]
- Each section was completed before moving to next? [YES/NO]
- Section tracking list updated after each section? [YES/NO]
- Section transition markers used? [YES/NO]
- Creative phases used for all major design decisions (Level 3-4)? [YES/NO/NA]
- Creative phase verification completed for each phase? [YES/NO/NA]

Read the full file on GitHub · 159 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 · 159 lines · 1,182 tokens per session scan A 00cae22a3b19

Subscribe to this mod's changes

verification-checklist is a cursor rule published in the GitHub repository kfnzero/mantis-mcp-server (10 stars, last pushed 1y ago), licensed MIT. It adds 1,182 tokens to every session, about $0.0059 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.