iteratively-verify

iteratively-verify is a command for Claude Code from Insight-Services-APAC/ingenious. It costs 0 tokens per session (548 once invoked), scanned A, original, MIT.

A command that checks a web application against every user story in a specification, fixes problems it finds, and repeats the check until the specified features work.

In plain words
What is it for?
Use it for end-to-end validation of web-app features, including deploying changes and confirming that fixes resolved the reported issues.
Why use it?
It combines testing, debugging, deployment checks, and re-testing so unfinished or broken user-facing behavior is not overlooked.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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 commands/insight-services-apac/ingenious/iteratively-verify
Clone the repo
git clone --depth 1 https://github.com/Insight-Services-APAC/ingenious

Made for: Claude Code.

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 iteratively-verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/insight-services-apac/ingenious/iteratively-verify.svg)](https://agentmods.dev/commands/insight-services-apac/ingenious/iteratively-verify)
Your own site
<a href="https://agentmods.dev/commands/insight-services-apac/ingenious/iteratively-verify"><img src="https://agentmods.dev/badge/commands/insight-services-apac/ingenious/iteratively-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 548 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 $0.00000 $0.00548
Opus 5 $0.00000 $0.00274
Sonnet 5 $0.00000 $0.00110
Haiku 4.5 $0.00000 $0.00055

Measured yesterday against content hash 24fb86c7b054, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

iteratively-verify 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.

.claude/commands/analysis/iteratively-verify.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Web App Development and Validation

Work autonomously to validate the application end-to-end per all User Stories in spec.md. Resolve all remaining issues until fully functional.

You cannot stop until everything in spec.md is implemented and validated.

Autonomous Work Expectations

  • Do not stop early - work until everything is complete
  • Do not stop tasks due to token budget concerns
  • Complete tasks fully, even if end of budget is approaching
  • Never artificially stop any task early regardless of context remaining

Required Work Cycle

For each and every feature in spec.md:

  1. Validate - Test the feature thoroughly
  2. Debug - Identify any issues found
  3. Implement - Code fixes and features as needed
  4. Unblock - Resolve all problems
  5. Re-validate - Confirm feature is fully functional
  6. Repeat - Move to next feature until all complete

Development Workflow

After any code change:

  1. Deploy changes immediately
  2. Confirm deployment successful
  3. Re-test functionality
  4. Proceed only after verifying stability

Debug cycle: Debug -> Fix -> Deploy -> Confirm resolution

Validation Requirements

Aspect Details
Source All User Stories in spec.md
Coverage Functional correctness, data consistency, state transitions, error handling

Validation workflow:

  1. Test feature end-to-end
  2. If issues found: debug, implement fixes, deploy
  3. Re-validate
  4. Repeat until feature is fully functional
  5. Move to next feature

Page requirements:

  • All functions fully implemented and data-driven (no hardcoded placeholders)
  • All routes accessible via UI
  • Document new components with behavior and state details
  • Map UI elements to corresponding User Stories

Specifications Compliance

spec.md is the authoritative source - all items must be completed.

If specifications are unclear, refine them to be explicit, structured, consistent, and agent-friendly while preserving original intent.

Read the full file on GitHub · 78 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 · 78 lines · 0 tokens per session scan A 24fb86c7b054

Subscribe to this mod's changes

iteratively-verify is a command published in the GitHub repository Insight-Services-APAC/ingenious (24 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 548 tokens. 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 2026-09-04.