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/plan-executionnpx skills add fmind/dotfiles --skill plan-executiongit 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 | $0.00045 | $0.01007 |
| Opus 5 | $0.00023 | $0.00504 |
| Sonnet 5 | $0.00009 | $0.00201 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
plan-execution 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 yesterday.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Execution
Turn an accepted plan into reviewable evidence while preserving the user's work and authority boundaries.
Preconditions
- Confirm the requested action includes implementation. A plan alone is not authorization to mutate the repository.
- Re-read the original request, accepted plan, repository instructions, and current status before the first edit.
- Preserve staged, unstaged, and untracked user work. Never reset, clean, stash, overwrite, or reformat unrelated files.
- Treat commit, push, pull request, issue mutation, deployment, infrastructure apply, external messaging, and publication as separate authorities.
- Stop rather than weaken an assertion, skip a gate, broaden an exclusion, or hide a warning.
Workflow
- Reconcile the plan: Verify that paths, symbols, dependency versions, commands, and assumptions still match the checkout. Amend the execution notes when reality differs; request direction if the required outcome would materially change.
- Capture the baseline: Record branch, HEAD, status, relevant test state, and known external boundaries. Identify which existing edits belong to the user.
- Order the work: Follow the dependency graph and critical path. Choose the smallest vertical slice that produces independently useful behavior and proof.
- Establish red evidence: Use test-driven-development for behavior changes or create a characterization test when changing legacy behavior. For non-code changes, define the failing contract or validation signal first.
- Implement minimally: Use the applicable language, infrastructure, site, or document skill. Touch only files traceable to the current slice and explain non-obvious trade-offs at the decision point.
- Verify the slice: Run the focused test, formatter, static checks, and any bounded runtime/manual check promised by the plan. Read the full output and fix root causes.
- Review the delta: Compare the actual diff with the intended slice. Remove only artifacts introduced by this work, confirm no requirement drift, and use diff-review for risky changes.
- Checkpoint honestly: Mark the slice complete only with fresh evidence. Record partial results, deviations, and residual gaps before moving on.
- Protect unrelated work: Before any full gate, inspect the full gate's task definition and working-tree state. If it runs whole-tree write-formatters and unrelated or user changes are present, validate the exact candidate in an isolated temporary worktree or run equivalent non-mutating checks; never reformat unrelated work.
- Run the whole contract: Test changed behavior first, then run the repository-owned full gate, normally
mise run all. Keep local, exact-head CI, runtime, deployed, and published evidence separate. - Hand off: Summarize changes, verification, untested boundaries, and remaining tasks. Leave the worktree for review unless further mutation was explicitly authorized.
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.
- yesterday First seen · 56 lines · 45 tokens per session scan A 854519dcade9
plan-execution is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 1,007 once invoked, about $0.0002 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…