Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/natsukium/dotfiles/attmcojp-claude-md)<a href="https://agentmods.dev/skills/natsukium/dotfiles/attmcojp-claude-md"><img src="https://agentmods.dev/badge/skills/natsukium/dotfiles/attmcojp-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.
<a href="https://agentmods.dev/skills/natsukium/dotfiles/attmcojp-claude-md"><img src="https://agentmods.dev/badge/skills/natsukium/dotfiles/attmcojp-claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00138 | $0.01323 |
| Opus 5 | $0.00069 | $0.00661 |
| Sonnet 5 | $0.00028 | $0.00265 |
| Haiku 4.5 | $0.00014 | $0.00132 |
Grade B, and why
attmcojp-claude-md scanned grade B 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 12d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
run, which needs sudo and is the user's call. Say so explicitly when reporting done — How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The attmcojp org-level CLAUDE.md
~/src/work/github.com/attmcojp/CLAUDE.md applies to every attmcojp checkout beneath it,
and it is not editable. It is a symlink into the sops-nix secret store, mode 0400,
replaced wholesale at the next activation. A write there fails; forcing the write to
succeed — chmod, replacing the symlink, writing through it — produces a change that the
next activation discards without warning. Never edit that path.
The source of truth is hosts/darwin/work/attmcojp-claude.md in the dotfiles repository,
encrypted with sops. The rules are attmcojp-internal and that repository is public, which
is why the file is encrypted rather than stored as text, and why the procedure below
never lets the plaintext enter a working tree.
Procedure
sops and treefmt live in the dotfiles devShell, not on the ambient PATH — bare
make fails with make: sops: No such file or directory. Run every command below
through nix develop --command with the dotfiles repo as the working directory:
the devShell hook acts on the cwd (installing pre-commit hooks, syncing files), so
launching it from another repository mutates that repository instead.
cd /Users/natsukium/src/private/github.com/natsukium/dotfiles
1. Decrypt. The path to the plaintext copy is printed on stdout.
nix develop --command make attmcojp-claude-md-open
2. Edit that file with the normal file tools. It sits under ~/.cache, deliberately
outside every git repository. Do not copy it anywhere else, and do not paste its contents
into a commit message, PR, issue, or any other repository.
3. Re-encrypt, which also deletes the plaintext copy.
nix develop --command make attmcojp-claude-md-seal
File has not changed, exiting (make exits 2) means the edit was a no-op. That is a
signal, not a broken command — report it rather than retrying.
Sealing deletes the plaintext copy only on success. Any failure leaves it in place on purpose, so an edit is never lost to a transient error; if the change is being abandoned rather than retried, remove it by hand:
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.
- 12d ago First seen · 114 lines · 138 tokens per session scan B bee6a0e1ffa7
attmcojp-claude-md is a skill published in the GitHub repository natsukium/dotfiles (103 stars, last pushed today), licensed CC0-1.0. It adds 138 tokens to every session and 1,323 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
deep-research-team
This skill should be used when the user asks for "deep research", "research team", "comprehensive analysis", "research report", "investigate thoroughly", "compare X vs Y in depth", or needs synthesis across multiple sources with verification. It spawns a coordinated team of researcher agents across multiple rounds…
audit-permissions
This skill should be used when the user asks to "audit claude permissions", "audit permissions", "review local claude settings", "promote permissions to global", "clean up claude settings", "find permission patterns", or wants to identify project-local Claude Code permissions that should be added to global…
malo-find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
start
Enable auto TTS for this session.
stop
Disable auto TTS for this session.
cancel
Stop any currently playing text-to-speech audio.