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-reviewnpx skills add fmind/dotfiles --skill plan-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 | $0.00047 | $0.00986 |
| Opus 5 | $0.00023 | $0.00493 |
| Sonnet 5 | $0.00009 | $0.00197 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
plan-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 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Review
Improve a plan by attacking its load-bearing assumptions while course correction is still cheap.
Review Boundary
- Review only unless the user explicitly requests revisions or implementation.
- Read the plan, its source requirements, repository reality, and available evidence. Do not review a summary when the full artifact is available.
- Steelman the intended outcome before criticizing the approach.
- Prefer five decision-changing findings over a long generic risk list.
- Do not inflate scope in the name of ambition. The strongest review may recommend a smaller plan, a cheaper test, or no build.
- Separate verified conflicts, evidence-backed risks, assumptions, and questions.
Lenses
Apply the lenses relevant to the plan and name which were used:
- Founder: Target user, painful job, wedge, why now, distribution, switching, monetization, defensibility, and kill assumptions.
- Product: Journey completeness, independent value, success metrics, guardrails, accessibility, trust, support, and learning loop.
- Engineering: Architecture, data flow, interfaces, invariants, failure handling, security, privacy, performance, compatibility, and maintainability.
- Delivery: Dependency order, vertical slices, test seams, migrations, observability, rollout, rollback, operational ownership, and authority boundaries.
Workflow
- Reconstruct intent: State the desired outcome, non-goals, constraints, evidence, and proof required for completion.
- Inspect current reality: Verify relevant source paths, interfaces, dependencies, runtime assumptions, and existing mechanisms the plan proposes to replace or duplicate.
- Map claims: Extract the decisions and assumptions on which the plan depends. Identify any requirement with no task, task with no requirement, or success claim with no proof.
- Challenge the premise: Ask whether the problem is real, the chosen scope is the smallest useful wedge, and a no-build or manual alternative could learn more cheaply.
- Attack failure modes: Imagine the plan failed through lack of value, integration breakage, data loss, abuse, operational burden, migration, adoption, or rollback failure. Trace concrete chains rather than naming categories.
- Test intended versus planned: Compare documented permissions, user journeys, data rules, and operational promises with the actual tasks and verification steps.
- Rank findings: Score each issue by impact, likelihood, confidence, and cheapness to test. Promote only issues that could change the decision or execution order.
- Offer remedies: Give the smallest corrective change, cheapest decisive test, and kill or rollback criterion. Present numbered alternatives when a real trade-off remains.
- Issue a verdict: Return
ACCEPT,ACCEPT WITH CHANGES,REVISE, orSTOP AND TEST, with the minimum conditions for the next state.
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 · 63 lines · 47 tokens per session scan A 9dec29791a4d
plan-review is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 986 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…