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 fmind/dotfiles --skill plan-reviewgit clone --depth 1 https://github.com/fmind/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/fmind/dotfiles/plan-review)<a href="https://agentmods.dev/skills/fmind/dotfiles/plan-review"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/plan-review/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/fmind/dotfiles/plan-review"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/plan-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00047 | $0.00986 |
| Opus 5.5 | $0.00019 | $0.00394 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 1mo ago), licensed MIT. It adds 47 tokens to every session and 986 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
full-review
Full review: read every repo area, apply verified fixes, and prove all checks pass.
duckdb
Query and export CSV, Parquet, JSON, or SQLite data with DuckDB.
observability
Instrument Python services and agents: structlog logs, OpenTelemetry traces and metrics.
resolve-conflicts
Resolve Git merge or rebase conflicts by both sides' intent; verify the result.
skill-security-review
Review third-party skills and agent extensions for supply-chain risk.
sops-secrets
Encrypt, rotate, and inject Git secrets with sops and age.