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 skills add aiya000/dotfiles --skill apply-to-agents-md-git-rootgit clone --depth 1 https://github.com/aiya000/dotfilesWrote 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/aiya000/dotfiles/apply-to-agents-md-git-root)<a href="https://agentmods.dev/skills/aiya000/dotfiles/apply-to-agents-md-git-root"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/apply-to-agents-md-git-root.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.00876 |
| Opus 5 | $0.00039 | $0.00438 |
| Sonnet 5 | $0.00015 | $0.00175 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
apply-to-agents-md-git-root 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 2d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
apply-to-agents-md-git-root
Distill useful information from the current session into the project's AGENTS.md, so future agents working in this repo start already knowing it.
Steps
-
Determine
{git-root}: rungit rev-parse --show-toplevel- If not in a git repository, stop and tell the user this skill requires a git repo
-
Review the current conversation for information that is:
- Non-obvious and not derivable by reading the code (a gotcha, a hidden dependency between components, a startup/recovery procedure, a networking quirk, an infra fact)
- Durable — true beyond this one conversation, not a one-off task detail
- Relevant to this repository specifically
Do not extract:
- Ephemeral task details, or a chronological blow-by-blow of what was done
- Anything already documented in
{git-root}/AGENTS.md,README.md, or derivable by reading the code / git log - Secrets or credentials
If nothing meets this bar, tell the user there's nothing worth recording and stop here
-
Read
{git-root}/AGENTS.mdif it exists -
Secret scan the new content before writing (see below)
-
Write the distilled information into
{git-root}/AGENTS.md:- Organize by topic/section — this is a living reference, not a chronological log
- Merge into existing sections where topically related; add new sections otherwise
- Keep entries concise — a fact, plus (where non-obvious) the reason it matters
-
If
{git-root}/CLAUDE.mddoes not already exist, create it with exactly this content and nothing else:Read `AGENTS.md` in this directory before doing anything else.- If
{git-root}/CLAUDE.mdalready exists, leave it untouched — do not modify or overwrite it
- If
-
Review what was just added to
AGENTS.md. If any of it is general-purpose (useful beyond this one repo — e.g. a Claude Code / sandbox behavior, a tool quirk, a workflow preference) and high-importance, use AskUserQuestion to ask whether to also apply it globally via theapply-to-claude-md-home-rootskill. If the user agrees, invoke that skill, handing it the relevant excerpt
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.
- 2d ago First seen · 70 lines · 77 tokens per session scan A 18cf2aef73ad
apply-to-agents-md-git-root is a skill published in the GitHub repository aiya000/dotfiles (19 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 876 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 2026-09-06.
Other skills, from other repositories
restart__pull_request
A pull-request restart workflow for replacing a messy review with a new pull request containing one clean commit and a summary of the earlier discussion.
rescue__pull_request_review
An automated workflow for handling GitHub pull-request review comments, applying requested code changes, committing them, and pushing them back.
submit__pull_request
An automated pull-request submission workflow. A pull request is a request for a code change to be reviewed and merged; this workflow writes its explanation, creates it, watches its automated checks, and fixes failed checks.
rescue__pull_request_conflict
An automated procedure for resolving merge conflicts in a pull request branch. A merge conflict happens when Git cannot combine competing changes by itself.
write__pull_request
A workflow for writing a pull request description, the explanation attached to a proposed code change for review. It analyses the changes and commit history.
monitor__ci_status
An automated monitor for GitHub Actions, the service that runs checks such as tests after code changes. It watches all checks after a pull request or a push to a pull-request branch and can invoke a failure-recovery process.