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 sebastienrousseau/dotfiles --skill dotfiles-bootstrapgit clone --depth 1 https://github.com/sebastienrousseau/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/sebastienrousseau/dotfiles/dotfiles-bootstrap)<a href="https://agentmods.dev/skills/sebastienrousseau/dotfiles/dotfiles-bootstrap"><img src="https://agentmods.dev/badge/skills/sebastienrousseau/dotfiles/dotfiles-bootstrap/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/sebastienrousseau/dotfiles/dotfiles-bootstrap"><img src="https://agentmods.dev/badge/skills/sebastienrousseau/dotfiles/dotfiles-bootstrap.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.01133 |
| Opus 5.5 | $0.00036 | $0.00453 |
| Sonnet 5.5 | $0.00018 | $0.00227 |
| Haiku 4.5 | $0.00009 | $0.00113 |
Grade A, and why
dotfiles-bootstrap 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dotfiles-bootstrap
Provision a new workstation from a public dotfiles repository through
the sebastienrousseau/dotfiles harness.
This skill is for Claude Code to invoke dot config init <user> on the user's behalf — most useful when the user says "set me up like Alice" or "bootstrap a fresh laptop using my GitHub dotfiles."
What this skill does
When invoked, it:
-
Verifies the target argument is one of:
- a GitHub username (e.g.
alice→ expands togithub.com/alice/dotfiles) - an
owner/repopair (e.g.alice/configs) - a full HTTPS or
git@host:pathclone URL
- a GitHub username (e.g.
-
Refuses plain
http://URLs (no transit integrity). -
Reads the user's current agent profile from
$DOT_AGENT_PROFILE(defaults toask):ask→ rundot config init <user> --dry-run(read-only preview)plan→ rundot config init <user> --dry-runand explain the planapply→ rundot config init <user> --yes(full apply withchezmoi apply), only after the user has confirmed they trust the repositoryaudit→ rundot config init <user> --no-apply --yes(clone only, no chezmoi apply), after the same confirmation
An agent has no terminal, so
dot config initrefuses to clone without--yes. Pass it only once the user has said yes to this repository. -
Surfaces the trust prompt warnings before any clone runs — the target repo's scripts execute with the user's privileges.
-
Reports the outcome (success / failed / aborted-by-trust-prompt) so the user can decide next steps.
Invocation pattern
# canonical
dot config init <user> # github.com/<user>/dotfiles
dot config init <owner>/<repo> # github.com/<owner>/<repo>
dot config init <https-or-ssh-url> # explicit URL
# safety flags
dot config init <user> --dry-run # preview only
dot config init <user> --no-apply # clone, skip chezmoi apply
dot config init <user> --force # overwrite existing chezmoi source dir
dot config init <user> --yes # consent without a terminal (required by agents)
What ships with it
1 file 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.
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.
- today Changed · +1 tokens per session fcae15c065dd
- 14d ago Changed · +3 lines 8529781b214e
- 21d ago Changed ee7f95de6344
- 1mo ago First seen · 85 lines · 88 tokens per session scan A 151ccb9083b3
dotfiles-bootstrap is a skill published in the GitHub repository sebastienrousseau/dotfiles (81 stars, last pushed today), licensed Apache-2.0. It adds 89 tokens to every session and 1,133 once invoked, about $0.0004 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.
Other skills, from other repositories
full-review
Full review or routine upkeep: read every repo area, fix tools, dead code, stale config, and ignore files, and prove all checks pass.
documentation-site
Build Zensical docs and course sites: navigation, API docs, Pages, MkDocs/Hugo migration.
auth-status
Check CLI and ADC logins across providers: expiry, scopes, re-login commands.
ast-grep
Search, outline, and rewrite code structurally with ast-grep rules.
colab
Run code on Colab GPUs or TPUs and track compute units.
duckdb
Query and export CSV, Parquet, JSON, or SQLite data with DuckDB.