A goal-driven command that works in repeated rounds: build, check, and have a separate reviewer judge whether the goal was met. It requires a checkable success condition before starting and stops at a round limit.

Use it for tasks that need iteration, such as making a command pass, ensuring a screen behaves correctly, or producing a file with required content.

It separates implementation from evaluation, reducing the risk of treating unfinished work as complete. Each round uses the previous findings to guide the next attempt.

How ikhanux/ai-coding-blueprint configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ikhanux/ai-coding-blueprint. 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/ikhanux/ai-coding-blueprint/main/.claude/commands/goal.md

Clone the repo

git clone --depth 1 https://github.com/ikhanux/ai-coding-blueprint

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/ikhanux/ai-coding-blueprint/goal/github.svg)](https://agentmods.dev/commands/ikhanux/ai-coding-blueprint/goal)

Your own site

<a href="https://agentmods.dev/commands/ikhanux/ai-coding-blueprint/goal"><img src="https://agentmods.dev/badge/commands/ikhanux/ai-coding-blueprint/goal/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/ikhanux/ai-coding-blueprint/goal"><img src="https://agentmods.dev/badge/commands/ikhanux/ai-coding-blueprint/goal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 520 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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.00520
Opus 5.5	$0.00012	$0.00208
Sonnet 5.5	$0.00006	$0.00104
Haiku 4.5	$0.00003	$0.00052

Measured 1mo ago against content hash ac3cc438b56f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

goal 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 1mo 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.

.claude/commands/goal.md · 46 lines

What it actually says

Goal

Goal: $ARGUMENTS

Work in rounds until the goal is genuinely met, judged by someone other than the agent that did the work. This exists because "I think it's done" and "it is done" are different things, and the difference is expensive.

0. Pin the success condition

Before any work, write down, in one or two lines, what "met" means in checkable terms: a command that must pass, a screen that must show X, a file that must exist with Y. If the goal as stated has no checkable condition, ask for one and stop. Do not start without it.

Note the round limit: 5 rounds, unless the user gave a different number.

1. Each round

Build: delegate the work per the delegation policy in CLAUDE.md (builder / ui-builder / page-scaffolder / ux-copy; debugger first if something is broken). Self-contained brief every time: the goal, the success condition, what the previous round found.
Check: run the success condition and the Check command from CLAUDE.md § Commands yourself. Paste the output.
Judge: hand the diff, the success condition and the output to a fresh code-reviewer with exactly this question: "Is the success condition met, yes or no, and what is the evidence?" The builder's own opinion does not count. The reviewer's verdict does.
Decide: met → go to Report. Not met → next round, with the reviewer's findings as the brief. Round limit hit → Report anyway.

Never reword the goal to make it easier to meet. Never mark it met on "should work".

2. Report

Rounds used, and what each one changed
The success condition, and the evaluator's final verdict with its evidence
The Check output from the last round
If the limit was hit: the specific blocker, what was tried, and what the user should decide

Say plainly whether the goal was met. If it was not, say so in the first line.

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.

1mo ago First seen · 46 lines · 31 tokens per session scan A ac3cc438b56f

Subscribe to this mod's changes

goal is a command published in the GitHub repository ikhanux/ai-coding-blueprint (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 520 once invoked, about $0.0001 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 2026-09-21.

Building agents Planning

goal next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
goalikhanux/ai-coding-blueprint	Command	2	1mo ago	MIT	A	31	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

ai-coding-blueprint: Command for Claude Code