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.
npx agentmods add instructions/alinotfoundbtw/sounding/claude-mdgit clone --depth 1 https://github.com/alinotfoundbtw/soundingWrote 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.
[](https://agentmods.dev/instructions/alinotfoundbtw/sounding/claude-md)<a href="https://agentmods.dev/instructions/alinotfoundbtw/sounding/claude-md"><img src="https://agentmods.dev/badge/instructions/alinotfoundbtw/sounding/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01750 | $0.01750 |
| Opus 5 | $0.00875 | $0.00875 |
| Sonnet 5 | $0.00350 | $0.00350 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
sounding CLAUDE.md 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Operating instructions for this repository. Read this before doing anything.
Identity
Everything public in this repo belongs to alinotfound.
- English only. No Persian anywhere — code, comments, commits, issues, releases, docs. Not in a commit message, not in a TODO.
- No real name. Never add one to a file, a commit author line, a changelog, a README, or an issue. If a config or credential surfaces one, stop and say so rather than committing it.
- The mark is
·)))and it belongs in the README footer and the console signature. Nowhere else. It is a signature, not decoration.
What this project is
sounding audits agent instructions — MCP servers, Agent Skills, and prompts —
for structural problems, scores them with a visible formula, writes the
corrections, and pins them so drift is caught.
The product is trustworthiness. Every decision follows from that:
- A finding without a reference is an opinion. This tool does not ship opinions.
- A score whose formula is hidden is a vibe. The formula is always printed.
- Nothing is written to disk without being shown first.
- Generated text that still needs a human says
TODOinside itself. - The tool states plainly what it does not check.
If a change makes the tool more impressive but less honest, it is the wrong change. Say so instead of making it.
Hard rules
These need explicit approval from the user, every time. Never assume it.
git push --forceor--force-with-leaseonmain- Deleting or renaming a repository, or changing its visibility
- Publishing to PyPI, npm, or any registry
- Rewriting history:
rebaseon pushed commits,filter-branch, amending a pushed commit - Adding a dependency — this package has zero and that is a feature
- Anything touching credentials, tokens, or
security.txtcontact details
Never, under any circumstances:
- Commit a secret, a token, an API key, or a
.envwith real values - Invent numbers. No download counts, no user counts, no benchmark results that were not actually measured. If a number appears in public text, it must be reproducible by running something in this repo.
- Add a badge for something that does not exist
- Write "trusted by" or testimonials
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.
- 3d ago First seen · 196 lines · 1,750 tokens per session scan A aaa142b1dc0f
sounding CLAUDE.md is an instructions file published in the GitHub repository alinotfoundbtw/sounding (4 stars, last pushed 8d ago), licensed MIT. It adds 1,750 tokens to every session, about $0.0088 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.
Other instructions, from other repositories
css-noop-checker CLAUDE.md
Instructions for purupurupu/css-noop-checker, covering claude.md, project overview, commands, tech stack and architecture.
css-noop-checker AGENTS.md
Instructions for purupurupu/css-noop-checker, covering ai agent instructions, project structure, adding a new rule, 1. create the rule file and 2. register in engine.ts.
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.