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 lacerbi/dotclaude --skill doublecheckgit clone --depth 1 https://github.com/lacerbi/dotclaudeWrote 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/lacerbi/dotclaude/doublecheck)<a href="https://agentmods.dev/skills/lacerbi/dotclaude/doublecheck"><img src="https://agentmods.dev/badge/skills/lacerbi/dotclaude/doublecheck/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/lacerbi/dotclaude/doublecheck"><img src="https://agentmods.dev/badge/skills/lacerbi/dotclaude/doublecheck.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 | $0.00013 | $0.01098 |
| Opus 5.5 | $0.00005 | $0.00439 |
| Sonnet 5.5 | $0.00003 | $0.00220 |
| Haiku 4.5 | $0.00001 | $0.00110 |
Grade A, and why
doublecheck 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Branch and files: !
git status --short --branch - Unstaged changes: !
git diff - Staged changes: !
git diff --cached
The injected diffs cover working-tree changes. If a diff was too large to inline and arrived as a file path with a preview, read that file (or have reviewers run git diff themselves). If relevant work was committed during this conversation, inspect the corresponding commit or branch diff too. Focus on work from this conversation unless otherwise specified; unrelated changes may belong to the user or another agent.
Your Task
Perform a meticulous verification and comprehensive review of all work done. Establish the actual change scope before reviewing. Treat verification as read-only unless the user explicitly asks for fixes.
Deploy one or more fresh-context Opus reviewers (see Agent Selection in the global CLAUDE.md, including the one-heavy-compute-agent rule), split by aspect as the size and complexity of the change warrant. Review directly yourself only when the change is so small that a reviewer would add nothing: the point of this skill is a review by agents that did not do the work and don't share its assumptions. A fresh-context reviewer knows nothing of this conversation, so brief each one with: the original goals and requirements, its exact scope (files, commits, or the plan file), what counts as a finding (below), and the report format (below).
Verify that:
- All changes align with the original goals and requirements
- Modifications preserve file integrity and correctness
- Nothing is missing or requires additional updates
- Changes work coherently together
Deeper Review
Go beyond surface-level correctness. Evaluate the work for:
- Completeness: Are all requirements addressed? Are there gaps, missing scenarios, or implicit expectations left unhandled?
- Correctness: Does the logic hold? Are there subtle errors, flawed assumptions, or reasoning gaps?
- Consistency: Do the changes match the provided or discussed specs? Do they follow the conventions and patterns already established in the project?
- Structural integrity: Is the work well-organized? Watch for unclear boundaries, redundancy, or unnecessary entanglement between parts that will make future changes harder.
- Consolidation: Flag spaghettification—duplicated logic, parallel structures doing similar things, components that could be merged or reused. In code: identify candidates for shared functions, similar modules that could be unified, redundant abstractions. In plans/docs: overlapping sections, repeated concepts, restated prerequisites or duplicated steps. Report what you find; do not refactor.
- Hazard avoidance: Identify footguns—things that look correct now but will mislead or break later (e.g., ambiguous naming, brittle assumptions, implicit dependencies, information that will drift out of sync).
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 Changed · +11 lines 402425a7fbfb
- 1mo ago First seen · 68 lines · 13 tokens per session scan A c4be28056fac
doublecheck is a skill published in the GitHub repository lacerbi/dotclaude (2 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 1,098 once invoked, about $0.0001 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
prove-me-wrong
Use when a leading diagnosis or nontrivial fix has initial support and needs one adversarial counterexample before acceptance.
reviewing-code
Reviews code changes for bugs, performance issues, security problems, and best practice violations. Use when reviewing PRs, before committing, after making code changes, or when user asks to review, check, or look over code. Catches N+1 queries, missing error handling, React hooks issues, test coverage gaps, and…
addressing-pr-feedback
Fetches, organizes, and addresses PR review comments from GitHub. Use when user asks to review PR comments, fix PR feedback, check what reviewers said, address review comments, or handle bot suggestions on a pull request. Triggers on "review PR", "fix comments", "PR feedback", "what did reviewers say", "address PR…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
react-patterns
React 19 performance patterns and composition architecture for Vite + Cloudflare projects. 50+ rules ranked by impact — eliminating waterfalls, bundle optimisation, re-render prevention, composition over boolean props, server/client boundaries, and React 19 APIs. Use when writing, reviewing, or refactoring React…
pr-description-writer
Redacta una descripción de pull request clara y estructurada a partir de un diff de git, resumen de rama o lista de commits. Úsalo cuando te pidan escribir una descripción de PR, redactar una solicitud de cambios o documentar cambios de código. Produce una descripción con resumen, motivación, cambios realizados, pasos…