supergoal

supergoal is a skill for Claude Code, Codex, Cursor from cskwork/supergoal-skill. It costs 77 tokens per session (3,085 once invoked), scanned A, original, MIT.

An objective-based development router for tasks such as fixing bugs, adding features, reviewing code, or mapping a codebase. It chooses a focused workflow and checks the result against evidence.

In plain words
What is it for?
It is for routing bug fixes, feature work, prototypes, quality checks, code reviews, architecture improvements, diagrams, and similar development tasks.
Why use it?
It helps turn a broad development request into the smallest useful change with a clear way to verify that the work is correct.

Skill for Claude CodeCodexCursor

Part of the supergoal plugin — 2 skills, 13 agents 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 skills/cskwork/supergoal-skill/supergoal
Any agent
npx skills add cskwork/supergoal-skill --skill supergoal
Clone the repo
git clone --depth 1 https://github.com/cskwork/supergoal-skill

Made for: Claude Code, Codex, Cursor.

Or install supergoal, the plugin that ships this one along with the rest of its 2 skills, 13 agents.

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 supergoal

README.md
[![agentmods](https://agentmods.dev/badge/skills/cskwork/supergoal-skill/supergoal.svg)](https://agentmods.dev/skills/cskwork/supergoal-skill/supergoal)
Your own site
<a href="https://agentmods.dev/skills/cskwork/supergoal-skill/supergoal"><img src="https://agentmods.dev/badge/skills/cskwork/supergoal-skill/supergoal.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,085 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 $0.00077 $0.03085
Opus 5 $0.00039 $0.01543
Sonnet 5 $0.00015 $0.00617
Haiku 4.5 $0.00008 $0.00309

Measured 5d ago against content hash f4ad76357f1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

supergoal 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 5d 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.

.cursor/skills/supergoal/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

About

One objective -> smallest correct change -> verified against ground truth. If invoked, run this skill's contract instead of downgrading to an inline shortcut. SKILL.md is the router; reference/ carries procedure. Unless explicitly invoked, pure brainstorming and user-driven step-by-step work use normal direct collaboration.

Standing rules (read first, every mode). Before classifying the mode, read .supergoal/rules/RULES.md if present. Honor it across phases as top-priority preference, but rules never weaken safety gates. Create/edit it only when the user explicitly asks (reference/rules.md). Check only the repo root (.supergoal/rules/RULES.md), and skip the check entirely in an ephemeral single-task workspace (auto-LIGHT tier; see role-loop ## Tier selection).

Core principles

  • Ground truth beats proxy: re-run REAL tests, re-read request/docs, and do not optimize to self-grading.
  • Exact proof beats review; implementation is delegated to a builder subagent.
  • LIGHT tier substitutes in-context equivalents for vault artifacts, gate scripts, the Z file, and the builder dispatch; its approval rule and commit bar live in reference/role-loop.md ## Tier selection.
  • Smallest correct change; match surrounding code. Scope-minimalism governs code surface area, not UI quality: polished user-facing UI is baseline correctness.
  • GREENFIELD / DEBUG / LEGACY code changes use Before/After Eval before Build: prove before, target after, and delta with trusted commands (reference/delivery-gate.md).
  • Ask only when genuinely ambiguous; resolve code-answerable questions by reading the code.
  • Report for humans: outcome first, Simplified Technical English prose, the project's own vocabulary (reference/reporting.md); machine-checked markers stay verbatim.
  • Docs language: for persistent repo docs (docs/**, run vaults, .domain-agent/**, ADR/spec/changelog), match the target repo's dominant prose language; mixed/none -> the user's language. Keep identifiers, paths, commands, and machine-checked anchors in canonical English so checks keep matching.
  • DEBUG done-bar: a green reported-repro is NOT done. Before commit, print three literal lines and satisfy them - GATE.owner= the invariant-owning frame (for a raised exception: the frame that RAISES it via the traceback, not where it surfaces; for recursion: inside the enumerated cycle), GATE.alt_repro= a structurally different second repro now passing, GATE.conformance= raw-literal returns reachable through the patched path (and its symmetric sibling methods) converted to the module's canonical forms (S.One over 1). Full rules: role-loop "DEBUG hidden-contract gate".
  • Hard stops: a destructive or irreversible step (drop data, force-push, external publish) needs explicit consent; if the real tests cannot pass, report it - never fake a pass.

Read the full file on GitHub · 139 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. 5d ago First seen · 139 lines · 77 tokens per session scan A f4ad76357f1f

Subscribe to this mod's changes

supergoal is a skill published in the GitHub repository cskwork/supergoal-skill (4 stars, last pushed 7d ago), licensed MIT. It adds 77 tokens to every session and 3,085 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

engine-api

The LLM-facing contract for the deterministic claude-wiki-pages Bun engine — how ANY agent should call it. Documents each subcommand (verify, fix, heal, doctor, config, migrate, search, snapshot; plus planned index/link-suggest), its --json output shape, exit codes, and when to call it on a write-path. Trigger when an…

odere-pro/claude-wiki-pages-plugin · 134 tokens

ingest-pipeline

The ingest pipeline's topic-tree plan format and confirmation gate, the opt-in destructive optimize (restructure) procedure, and the final-report template for claude-wiki-pages. Documents the plan/approval and restructure steps so the ingest agent can drive them without inlining the detail. Trigger when an agent or…

odere-pro/claude-wiki-pages-plugin · 104 tokens

ingest

Ingest one or more sources from vault/raw/ into typed wiki pages under vault/wiki/. Trigger when the user says "ingest this source", "process the file I just dropped in raw/", "add this to the wiki", or invokes /claude-wiki-pages:ingest directly. Prefer the pipeline (/claude-wiki-pages:claude-wiki-pages-ingest-agent)…

odere-pro/claude-wiki-pages-plugin · 94 tokens

obsidian-graph-colors

Apply color groups to Obsidian's graph view so each topic branch has a distinct color. Use when the user says "color the graph", "graph colors", "update graph colors", "add topic color", or after creating new topic folders that need a color assignment.

odere-pro/claude-wiki-pages-plugin · 62 tokens

search

Find wiki pages by keyword with a deterministic, reproducible ranking and [[wikilink]]-ready results. Trigger when the user or an agent wants to locate pages ("find pages about X", "which pages mention Y", "list notes tagged Z") or needs a candidate set before a deeper query/synthesis. Backed by the engine search…

odere-pro/claude-wiki-pages-plugin · 119 tokens

curator-fixes

The curator's supplemental diagnostic checks, the nine safe auto-fixes, the automatic judgment-fix procedure, and the lint-report template for claude-wiki-pages. Documents what the curator checks and how it repairs wiki structure under a git checkpoint, so the curator agent can apply fixes without inlining the…

odere-pro/claude-wiki-pages-plugin · 110 tokens