katgpt-rs: Skill for Claude Code

.agents/skills/goat-audit/SKILL.md

goat-audit is a skill for Claude Code, Codex from katopz/katgpt-rs. It costs 116 tokens per session (6,822 once invoked), scanned A, original, MIT.

A cross-repository audit for checking whether shared GOAT or gain primitives from katgpt-rs are being used correctly by riir-* repositories. A repository is a code project, and a primitive is a reusable building block.

In plain words
What is it for?
Use it for quarterly maintenance, before planning work that depends on katgpt-rs, or when checking for stalled adoption, duplicated implementations, incorrect layering, and fork drift.
Why use it?
It finds shared components that were added but never connected, duplicated code that should be reused, and integrations placed in the wrong software layer.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is katopz/katgpt-rs's own configuration. It tells Claude Code and Codex how to work on katgpt-rs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything katgpt-rs configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/katopz/git.

Reuse

Borrowing it

Nothing to install: this file belongs to katopz/katgpt-rs. 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/katopz/katgpt-rs/develop/.agents/skills/goat-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/katopz/katgpt-rs

Made for: Claude Code, Codex.

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 goat-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/katopz/katgpt-rs/goat-audit/github.svg)](https://agentmods.dev/skills/katopz/katgpt-rs/goat-audit)
Your own site
<a href="https://agentmods.dev/skills/katopz/katgpt-rs/goat-audit"><img src="https://agentmods.dev/badge/skills/katopz/katgpt-rs/goat-audit/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.

agentmods 80×15 button for goat-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/katopz/katgpt-rs/goat-audit"><img src="https://agentmods.dev/badge/skills/katopz/katgpt-rs/goat-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,822 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00116 $0.06822
Opus 5 $0.00058 $0.03411
Sonnet 5 $0.00023 $0.01364
Haiku 4.5 $0.00012 $0.00682

Measured today against content hash 8b64e81c61d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

goat-audit 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 today.

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.

.agents/skills/goat-audit/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

goat-audit — Cross-Repo GOAT/Gain Cherry-Pick Audit

Use this skill when auditing whether the riir-* private repos have consumed the GOAT-validated primitives shipped in katgpt-rs. It detects four failure classes:

  1. Stalls — primitive default-on in katgpt-rs for ≥7 days, zero runtime wiring in riir-*.
  2. DRY violations — riir-* ships a local copy of substrate that should consume katgpt-core / katgpt-transformer / katgpt-pruners.
  3. SOLID violations — primitive consumed in the wrong layer (e.g. a sync-boundary primitive wired into a latent-only runtime, or vice versa).
  4. Fork drift (the Issue 019 class) — riir-* is a fork of katgpt-rs (e.g. riir-engine/src/lib.rs says "Extracted from katgpt-rs (MIT, frozen at v0.1.0)") and a Layer 2 struct-name grep hits a file that defines its own pub struct SameName with zero use katgpt_*:: imports. The audit must distinguish consumer (true positive, primitive wired) from duplicate (false positive, primitive re-implemented locally — the canonical has bit-rotted since v0.1.0).

When to use

  • Quarterly hygiene gate — re-audit after every major katgpt-rs release.
  • Before opening a plan that consumes a katgpt-rs primitive — confirm it isn't already wired (avoid duplicate work).
  • When a user asks "did riir-* get every good thing from katgpt-rs yet?" (the canonical trigger).
  • After a promotion in katgpt-rs — track that the riir-* runtime wiring plan is filed within 7 days.

DO NOT use for

  • Paper distillation (use the research skill).
  • Single-repo refactors with no cross-repo angle.
  • Bug fixes with no architectural impact.

Repos in scope (the product set of 8 — audit focuses on the 4 cherry-pick targets)

Canonical list: katgpt-rs/AGENTS.md §"Repo count". riir-dapps (dApp layer, added 2026-08-20) is the 8th and is OUT OF SCOPE here for the same reason as riir-game-sdk: it composes outcomes, it hosts no feature-gated katgpt primitive to audit.

katgpt-rs          ← public engine (substrate: katgpt-core + 16 leaf crates + root)
riir-ai            ← private runtime/game (cognitive, ARG, CLR, HLA, karc, cwm, etc.)
riir-chain         ← private chain (LatCal, quorum, asset lifecycle)
riir-neuron-db     ← private neuron-shard leaf (Pod, freeze, consolidation, AnyRAG)
riir-train         ← private training vault (OUT OF SCOPE — training-only methods)
riir-game-sdk      ← private game-vocabulary facade + dev-tool workspace (OUT OF SCOPE —
                      consumes vocabulary from riir-games-shared in riir-ai, not katgpt-rs
                      engine primitives directly; transitively reaches katgpt-core only via
                      the always-on path dep, no feature-flag-gated primitives to audit)

Read the full file on GitHub · 255 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. today Changed · +1 lines 8b64e81c61d7
  2. 7d ago Changed · +27 lines 7b429e39eac7
  3. 11d ago First seen · 227 lines · 116 tokens per session scan A c9f72d47233d

Subscribe to this mod's changes

goat-audit is a skill published in the GitHub repository katopz/katgpt-rs (98 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 6,822 once invoked, about $0.0006 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 skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

nvca-chart-release

Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.

NVIDIA/nvcf · 61 tokens