memorykit: Command for GitHub Copilot

.github/prompts/verify-claim.prompt.md

verify-claim is a command for GitHub Copilot from rapozoantonio/memorykit. It costs 11 tokens per session (725 once invoked), scanned A, original, MIT.

A pre-change verification checklist for an AI coding agent. It searches the codebase and project dependency files to confirm that named files, functions, patterns, APIs, and dependencies really exist before implementation begins.

In plain words
What is it for?
Use it before changing code to verify file paths, API usage, project conventions, dependencies, and existing implementations.
Why use it?
It reduces mistakes caused by assuming that a file, framework method, or package is available. It also reveals similar existing code and reports any remaining uncertainty.

Command for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt. Also seen: agent in frontmatter.

This is rapozoantonio/memorykit's own configuration. It tells GitHub Copilot how to work on memorykit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything memorykit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rapozoantonio/memorykit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rapozoantonio/memorykit/main/.github/prompts/verify-claim.prompt.md
Clone the repo
git clone --depth 1 https://github.com/rapozoantonio/memorykit

Made for: GitHub Copilot.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for verify-claim

README.md
[![agentmods](https://agentmods.dev/badge/commands/rapozoantonio/memorykit/verify-claim/github.svg)](https://agentmods.dev/commands/rapozoantonio/memorykit/verify-claim)
Your own site
<a href="https://agentmods.dev/commands/rapozoantonio/memorykit/verify-claim"><img src="https://agentmods.dev/badge/commands/rapozoantonio/memorykit/verify-claim/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for verify-claim

Your own site · 80×15
<a href="https://agentmods.dev/commands/rapozoantonio/memorykit/verify-claim"><img src="https://agentmods.dev/badge/commands/rapozoantonio/memorykit/verify-claim.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 725 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00011 $0.00725
Opus 5.5 $0.00004 $0.00290
Sonnet 5.5 $0.00002 $0.00145
Haiku 4.5 $0.00001 $0.00072

Measured 12d ago against content hash 271f65735f97, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-claim 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 12d 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.

.github/prompts/verify-claim.prompt.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL: Verify before implementing

Before making ANY code changes, verify the following using available tools:

File Existence

  • Use #tool:search/codebase to confirm files exist at claimed paths
  • Use #tool:search to verify functions/classes mentioned exist
  • List actual files that will be modified with full paths

Pattern Verification

  • Search for similar existing patterns in the codebase
  • Confirm the approach matches existing conventions
  • Verify imports/dependencies are already used elsewhere

API/Framework Usage

  • If using a framework method, search codebase for examples
  • Verify the API signature matches what you're claiming
  • Don't assume methods exist - find evidence first

Dependencies

  • Check package.json / requirements.txt / go.mod for existing dependencies
  • Don't suggest adding dependencies unless verified they're needed
  • Search if functionality already exists in codebase

Report Format

✅ Verification Complete:
- Files exist: [list]
- Patterns found: [examples from codebase]
- Dependencies present: [list]
- Similar implementations: [file:line references]

⚠️ Concerns:
- [Any gaps or uncertainties]

Ready to proceed: Yes/No

Only proceed if verification passes.


**Usage**: Type `/verify` before asking agent to implement complex features

---

## 4. Recommended Workflow

### Option A: Full Workflow (Complex Features)
  1. Planner Agent: "Plan a feature for [description]"
  2. Review plan mentally or with /review
  3. Builder Agent: "Implement the plan above"
  4. Builder hands off → Reviewer Agent (automatic via handoff)
  5. Fix issues if needed

### Option B: Quick Implementation (Simple Tasks)
  1. Builder Agent: "Add [simple feature]"
  2. /review after completion

### Option C: Verification First (Uncertain Tasks)
  1. /verify the approach first
  2. Builder Agent: implement after verification passes
  3. /review after completion

---

## 5. VS Code Agent Picker Configuration

After creating these files, your agent picker will show:

Read the full file on GitHub · 133 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. 12d ago First seen · 133 lines · 11 tokens per session scan A 271f65735f97

Subscribe to this mod's changes

verify-claim is a command published in the GitHub repository rapozoantonio/memorykit (4 stars, last pushed 13d ago), licensed MIT. It adds 11 tokens to every session and 725 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-10-17.