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 skills/fmind/dotfiles/full-reviewnpx skills add fmind/dotfiles --skill full-reviewgit clone --depth 1 https://github.com/fmind/dotfilesWhat 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 | $0.00026 | $0.00988 |
| Opus 5 | $0.00013 | $0.00494 |
| Sonnet 5 | $0.00005 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
full-review 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Repository Review
Confirm this dotfiles repo is healthy end to end: the local gate is green, dot works, every pinned tool/dependency is current, and AGENTS.md/README.md/skills/ still describe the live repo. Every step below is read-only or idempotent — no chezmoi apply, no mise upgrade, no mise run release, no mise run prune.
1. Validate the gate
mise run check # check:actions, check:chezmoi, check:dprint, check:docs, check:go, check:leaks, check:lua, check:python, check:scan, check:shell, check:skills
mise run test # Go (dot/) + Python (skills/python-stack) suites
mise run build # compiles the dot binary
check:docs and check:skills already assert consistency between the documentation and the live CLI (mise tasks, dot commands, the AGENTS.md layout inventory, every SKILL.md under skills/ and .agents/skills/) — a green check:docs proves that layer; don't hand-re-audit it.
2. Confirm the dot CLI
dot verify # sanity checks: environment, tools, secrets, install freshness
dot --help # every subcommand needs an alias, matching skills/dot-cli/SKILL.md
dot status # git/docker/k3d smoke test
mise run doctor # chezmoi doctor + mise doctor
mise run diff # pending chezmoi diff, read-only
Only treat a dot verify failure as a repo bug when it is not explained by local environment state (an unauthenticated CLI, a missing optional secret) — those are sandbox facts, not defects.
3. Check tool and dependency currency (report, don't bump)
mise outdated # repo-scoped tools
mise -C "$HOME" outdated # global tool list
mise --version # warns here when mise itself is behind: `mise self-update`
go -C dot list -m -u all # Go module updates
mise outdated only covers mise-managed pins. Also scan what it can't see: action versions in .github/workflows/*.yml, plugin versions in dprint.json, and any exact-version (not "latest") tool pin in dot_config/mise/config.toml.tmpl. If something is genuinely stale, don't bump it here — hand off to upgrade-tools, one ecosystem at a time, validating after each.
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 · 64 lines · 26 tokens per session scan A 84dd8328d21d
full-review is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 988 once invoked, about $0.0001 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 skills, from other repositories
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
aiq-research
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
obsidian-bases
Obsidian Bases database feature for YAML-based interactive note views. Use when creating .base files, writing filter queries, building formulas, configuring table/card views, or working with Obsidian properties and frontmatter databases.
telegram
Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…
chezmoi-expert
Comprehensive chezmoi dotfiles management expertise including templates, cross-platform configuration, file naming conventions, and troubleshooting. Covers source directory management, reproducible environment setup, and chezmoi templating with Go templates. Use when user mentions chezmoi, dotfiles, cross-platform…