What is supergoal CLAUDE.md?

A repository guide for Claude Code, an AI coding tool, explaining where project instructions, source files, reference documents, and scripts are located.

Use it when working on the Supergoal plugin, especially before editing its skill instructions, supporting documents, or run-claim script.

It gives the coding agent a quick orientation and points it to the documents and files that govern changes in the project.

How robzilla1738/supergoal configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to robzilla1738/supergoal. 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/robzilla1738/supergoal/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/robzilla1738/supergoal

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/instructions/robzilla1738/supergoal/claude-md/github.svg)](https://agentmods.dev/instructions/robzilla1738/supergoal/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/robzilla1738/supergoal/claude-md"><img src="https://agentmods.dev/badge/instructions/robzilla1738/supergoal/claude-md/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/instructions/robzilla1738/supergoal/claude-md"><img src="https://agentmods.dev/badge/instructions/robzilla1738/supergoal/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,555 This file is loaded in full into every session.

When invoked 2,555 The same file — it is already loaded in full.

Security scan C 1 finding. 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	$0.02555	$0.02555
Opus 5.5	$0.01022	$0.01022
Sonnet 5.5	$0.00511	$0.00511
Haiku 4.5	$0.00255	$0.00255

Measured 2mo ago against content hash 470ec0c5d723, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

supergoal CLAUDE.md scanned grade C with 1 finding 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 2mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.codex/skills/supergoal

CLAUDE.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project-level instructions for Claude Code sessions opened in this repo. Read AGENTS.md first for the authoritative project doc; this file adds Claude-Code-specific tips on top.

Quick orientation

This repo is the source of truth for the supergoal skill — a Claude Code plugin that turns vague build requests into deeply-planned, autonomously-executed /goal runs with a final audit pass.

Full project doc: see AGENTS.md.

Working in this repo from Claude Code

File map you actually edit

skills/supergoal/SKILL.md — the skill content. Edit here for behavioral changes. ~565 lines (grew with v0.7's Stage 0 namespace-claim section; phase-loop section duplicates PROTOCOL.md and is a slim-down candidate).
skills/supergoal/references/*.md — progressive-disclosure docs the agent reads when needed (planning-depth.md, phase-design.md, goal-format.md, repo-state-comparison.md).
skills/supergoal/scripts/claim-run.sh — atomically claims a unique per-run dir (.supergoal/<slug>-XXXXXX via mktemp -d) so concurrent runs in one working tree can't clobber each other. Edit here to change the namespacing/slug logic; tested by tests/claim-run.test.sh.
skills/supergoal/scripts/repo-state.sh — the complete-working-tree-vs-baseline comparison helper. Edit here to change how the audit/cleanliness checks detect committed/staged/unstaged/deleted/untracked work. Copied into the run's .supergoal/<run-id>/ dir at Stage 7; tested by tests/repo-state.test.sh.
skills/supergoal/templates/PROTOCOL.md — execution loop + failure recovery + final audit. Edit here when changing the per-/goal-session protocol. Paths use the {{RUN_ROOT}} placeholder, sed-substituted to the concrete run dir at Stage 7.
skills/supergoal/templates/STATE.md — live-progress template the planner copies to <run-root>/STATE.md per run. Contains Run root: (this run's namespaced dir) and Baseline ref: (the HEAD sha captured at Stage 7 dispatch; the audit + cleanliness checks compare the complete working tree against it via repo-state.sh).
skills/supergoal/templates/ROADMAP.md — phase plan with Deliverables: bullets; the audit's deliverable check parses these bullets directly.
tests/claim-run.test.sh — fixture tests for claim-run.sh, incl. the concurrent-claim race (repo-only; run with bash tests/claim-run.test.sh).
tests/repo-state.test.sh — fixture tests for repo-state.sh (repo-only; run with bash tests/repo-state.test.sh).
.claude-plugin/plugin.json — bump version on every shipped change so the marketplace cache refreshes.
CHANGELOG.md — add a top entry per release.
README.md — public-facing only. Edit for docs / Mermaid diagram tweaks. No version bump needed.

Read the full file on GitHub · 118 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.

2mo ago First seen · 118 lines · 2,555 tokens per session scan C 470ec0c5d723

Subscribe to this mod's changes

supergoal CLAUDE.md is an instructions file published in the GitHub repository robzilla1738/supergoal (684 stars, last pushed 2mo ago), licensed MIT. It adds 2,555 tokens to every session, about $0.0102 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

supergoal CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
supergoal CLAUDE.mdrobzilla1738/supergoal	Instructions file	684	2mo ago	MIT	C	2,555	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

supergoal: Instructions file for Claude Code