What is fuck-my-shit-mountain?

A structured audit process for examining a software repository across areas such as architecture, security, performance, testing, maintainability, and release readiness.

It helps perform full or focused audits of a codebase, including security, stability, testing, documentation, privacy, accessibility, configuration, dependencies, and other quality areas.

It replaces scattered code checks with an evidence-based report that identifies problems across the project and records actionable findings.

fuck-my-shit-mountain — Skill for Codex by XiNian-dada

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.

Any agent

npx skills add XiNian-dada/Fuck_My_Shit_Mountain --skill fuck-my-shit-mountain

Clone the repo

git clone --depth 1 https://github.com/XiNian-dada/Fuck_My_Shit_Mountain

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xinian-dada/fuck_my_shit_mountain/fuck-my-shit-mountain/github.svg)](https://agentmods.dev/skills/xinian-dada/fuck_my_shit_mountain/fuck-my-shit-mountain)

Your own site

<a href="https://agentmods.dev/skills/xinian-dada/fuck_my_shit_mountain/fuck-my-shit-mountain"><img src="https://agentmods.dev/badge/skills/xinian-dada/fuck_my_shit_mountain/fuck-my-shit-mountain/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/skills/xinian-dada/fuck_my_shit_mountain/fuck-my-shit-mountain"><img src="https://agentmods.dev/badge/skills/xinian-dada/fuck_my_shit_mountain/fuck-my-shit-mountain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,558 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00059	$0.02558
Opus 5.5	$0.00024	$0.01023
Sonnet 5.5	$0.00012	$0.00512
Haiku 4.5	$0.00006	$0.00256

Measured 25d ago against content hash dde3f80bd0c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fuck-my-shit-mountain 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 25d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/package_skill.py, scripts/project_inventory.py, scripts/report_lint.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

fuck-my-shit-mountain/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fuck My Shit Mountain

Produce a calm, evidence-based audit that identifies realistic risks, explains their impact, and proposes the smallest practical fixes.

Resolve the Request

Use the user's existing choices and authorization. Do not ask again for supplied information.

Modes: Map natural-language concerns to the modes below. Default a general repository health audit to full. If the request leaves a material scope ambiguity, inventory the project with scripts/project_inventory.py <project-root> --format json and offer a few localized choices, then ask only about that ambiguity.
Format & HTML Theme: Default to stdout. Accept md, html, json, or both (Markdown + HTML) when requested. Write complete files to the requested location. Otherwise use audit-report-<project>-<date>.<ext> in the project root; use a time suffix if that name exists. Do not overwrite an earlier report accidentally.
- When html or both is requested, check if an HTML theme was specified (classic/legacy, obsidian, swiss, aurora, or random).
- If no theme was specified, ask the user whether they prefer the classic template or one of the three new designs:
  1. 旧版经典 (classic — templates/audit-report.html)
  2. 新版 · 黑曜极客 (obsidian — templates/audit-report-obsidian.html，Raycast/Linear 暗黑硬核风格)
  3. 新版 · 瑞士极简 (swiss — templates/audit-report-swiss.html，Stripe Press 典雅纸质风，打印/汇报首选)
  4. 新版 · 极光控制台 (aurora — templates/audit-report-aurora.html，现代交互控制台，支持日夜模式切换与即时搜索)
  5. AI 随机挑选新版 (random — 由 AI 从 3 款新版中随机选择一款)
- If random is selected, pick one among obsidian, swiss, or aurora. Load the corresponding template from templates/.
History: Save history only when the user requests it, to their chosen directory or .audit-reports/history/. Record timestamp, resolved commit(s), dirty worktree state, modes, scope, assessed scores, finding counts, and report path. stdout alone creates no files.

Read the full file on GitHub · 99 lines

Files

What ships with it

53 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

25d ago Changed · +6 lines dde3f80bd0c8
1mo ago Changed · -94 lines · -48 tokens per session 7e22dcaf1011
2mo ago First seen · 187 lines · 107 tokens per session scan A 585efd5c8b21

Subscribe to this mod's changes

fuck-my-shit-mountain is a skill published in the GitHub repository XiNian-dada/Fuck_My_Shit_Mountain (506 stars, last pushed 25d ago), licensed MIT. It adds 59 tokens to every session and 2,558 once invoked, about $0.0002 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 2026-08-30.

Code review

fuck-my-shit-mountain next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fuck-my-shit-mountainXiNian-dada/Fuck_My_Shit_Mountain	Skill	506	25d ago	MIT	A	59	Codex
autoreviewopenclaw/clawhub	Skill	9.5k	yesterday	MIT	A	17	Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills	Skill	2.2k	5d ago	MIT	A	115	Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermes	Skill	5.2k	yesterday	MIT	A	48	Claude Code, Codex
revdiff-planumputun/revdiff	Skill	945	yesterday	MIT	A	84	Claude Code
explore-unknownsdzhng/skills	Skill	1.4k	2d ago	MIT	A	162	Claude Code, Codex
re0-mergeLilMGenius/paperthin	Skill	1.4k	4d ago	MIT	A	70	Claude Code