assumption-checker

assumption-checker is an agent for Claude Code from a-ariff/ariff-claude-plugins. It costs 15 tokens per session (458 once invoked), scanned A, original, MIT.

A verification procedure for checking assumptions before an agent changes code or uses project details.

In plain words
What is it for?
It helps verify files, dependencies, function signatures, configuration values, database schemas, and the user's intended outcome before taking action.
Why use it?
It reduces errors caused by guessed file paths, package versions, API endpoints, environment settings, database structures, or unclear requirements.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the assumption-checker plugin — 1 agent shipped together

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 agents/a-ariff/ariff-claude-plugins/assumption-checker
Clone the repo
git clone --depth 1 https://github.com/a-ariff/ariff-claude-plugins

Made for: Claude Code.

Or install assumption-checker, the plugin that ships this one along with the rest of its 1 agent.

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 assumption-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/a-ariff/ariff-claude-plugins/assumption-checker.svg)](https://agentmods.dev/agents/a-ariff/ariff-claude-plugins/assumption-checker)
Your own site
<a href="https://agentmods.dev/agents/a-ariff/ariff-claude-plugins/assumption-checker"><img src="https://agentmods.dev/badge/agents/a-ariff/ariff-claude-plugins/assumption-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 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 5.1 $0.00015 $0.00458
Opus 5 $0.00008 $0.00229
Sonnet 5 $0.00003 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 6d ago against content hash 2c09d2c03247, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

assumption-checker 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 6d 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.

plugins/assumption-checker/agents/assumption-checker.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Assumption Checker Agent

Purpose

Prevents agent hallucinations and incorrect assumptions by requiring explicit verification before taking action on ambiguous or uncertain contexts.

When to Invoke

  • Before making changes based on inferred (not stated) requirements
  • When file paths, variable names, or configurations are guessed
  • When the user's intent could be interpreted multiple ways
  • Before assuming technology stack, framework versions, or dependencies

Validation Rules

NEVER Assume

  1. File locations - Always verify paths exist before referencing
  2. Package versions - Check package.json/requirements.txt for actual versions
  3. API endpoints - Verify endpoints exist in codebase before calling
  4. Environment variables - Confirm they exist before using
  5. Database schemas - Check actual schema before writing queries
  6. User intent - If ambiguous, ask clarifying questions

ALWAYS Verify

□ Does the file/path actually exist?
□ Is the function/method signature correct?
□ Are the dependencies actually installed?
□ Is the configuration value real or assumed?
□ Did the user explicitly state this requirement?

Response Pattern

When an assumption is detected:

⚠️ **Assumption Detected**

I was about to assume: [what was assumed]
Actual state: [unknown/needs verification]

**Before proceeding, please confirm:**
1. [Specific question 1]
2. [Specific question 2]

Or I can verify by: [how to check]

Anti-Patterns to Prevent

Bad Pattern Correction
"I'll use the config.ts file..." First: ls -la to verify it exists
"Since you're using React..." First: Check package.json
"The API endpoint is /api/users..." First: Search codebase for actual routes
"I'll update the database schema..." First: Check actual migration files

Strict Mode

This agent operates in strict mode - it will halt execution and request confirmation rather than proceeding with assumptions.

Read the full file on GitHub · 65 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. 6d ago First seen · 65 lines · 15 tokens per session scan A 2c09d2c03247

Subscribe to this mod's changes

assumption-checker is an agent published in the GitHub repository a-ariff/ariff-claude-plugins (14 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 458 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

autoresearch-orchestrator

Use this agent to run an autoresearch experiment session end-to-end — setup, baseline, and a batch of edit→measure→keep/discard experiments — and return a structured checkpoint. Typical triggers include the /run-autoresearch command dispatching a new optimization goal, resuming an existing session found in…

proyecto26/autoresearch-ai-plugin · 115 tokens

task-executor

Use this agent to monitor or debug autonomous task execution. Examples - "Why did my task fail?", "Show me the output from the last task run", "Check if the taskrunner is still running".

Stackbilt-dev/cc-taskrunner · 45 tokens

flow-optimizer

Keitaro flow health and optimization agent. Checks flow structure, weight distribution, filter configuration, dead landings, and suggests rebalancing.

iso73-ops/claude-keitaro · 33 tokens

landing-generator

Generates landing page and prelanding HTML content for affiliate verticals. Creates advertorials, quiz funnels, product pages, white pages, and registration forms optimized for conversion.

iso73-ops/claude-keitaro · 38 tokens

campaign-analyzer

Keitaro campaign performance analyzer. Pulls reports via API, evaluates campaign health, identifies kill/scale candidates, checks for spending without conversions.

iso73-ops/claude-keitaro · 33 tokens

frontend-design-enhancer

Enhances frontend design quality by applying aesthetic principles, avoiding generic AI defaults, implementing distinctive typography/color/animations, and creating polished user experiences.

bejranonda/LLM-Autonomous-Agent-Plugin-for-Claude · 32 tokens