pedantic-review

pedantic-review is a skill for Claude Code from flurdy/agent-skills. It costs 39 tokens per session (1,643 once invoked), scanned A, original, MIT.

A strict self-review of code changes focused on craftsmanship, reuse, structure, project conventions, and test coverage. It uses common software principles such as keeping code simple and avoiding unnecessary work.

In plain words
What is it for?
Use it before opening a pull request, after refactoring, or when checking whether new code fits existing conventions and has enough tests.
Why use it?
It helps find rushed decisions and maintainability problems before a change reaches human review.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Good fit Use it before opening a pull request, after refactoring, or when checking whether new code fits existing conventions and has enough tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flurdy/agent-skills/pedantic-review
Install

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.

Any agent
npx skills add flurdy/agent-skills --skill pedantic-review
Clone the repo
git clone --depth 1 https://github.com/flurdy/agent-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for pedantic-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/flurdy/agent-skills/pedantic-review/github.svg)](https://agentmods.dev/skills/flurdy/agent-skills/pedantic-review)
Your own site
<a href="https://agentmods.dev/skills/flurdy/agent-skills/pedantic-review"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/pedantic-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.

agentmods 80×15 button for pedantic-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/flurdy/agent-skills/pedantic-review"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/pedantic-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,643 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.01643
Opus 5 $0.00019 $0.00822
Sonnet 5 $0.00008 $0.00329
Haiku 4.5 $0.00004 $0.00164

Measured 2d ago against content hash f89fbf7c94af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pedantic-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.

The scan reads SKILL.md. This mod also ships 1 executable file (tests/test-skill-contract.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/pedantic-review/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pedantic Review

An opinionated read-only craft review, not a second requirements or correctness gate. Compare changed code with repository practice before recommending a cleaner design. No automatic fixes.

Ownership

Question Owner
Is the plan coherent? architect
Implement or repair the behavior? develop / implement-solution, separately authorized
Does the implementation meet requirements; are tests adequate and passing? verify-task
Does it format and lint? clean-code
Is the craft any good? pedantic-review
Is the exact PR correct and supported by review evidence? review-pr
What independent claims merit validation? second-opinion

Do not run those workflows automatically. Reuse a supplied scope/requirements packet; never replace a caller's revision with the default branch diff. A craft verdict cannot clear the overall review, prove requirements satisfied, establish coverage sufficiency, or authorize publication.

Usage

/pedantic-review                  # current changes against the verified default-branch base
/pedantic-review --base <ref>      # explicit comparison base, including trunk work
/pedantic-review --uncommitted    # staged, unstaged, and selected untracked changes
/pedantic-review --staged         # index scope only
/pedantic-review --pr <selector>  # qualified PR, URL, or current-repository shorthand
/pedantic-review --verbose        # include subjective Consider findings

Honor the premium route. If reduced capability is known, disclose it and ask to continue or stop, unless the user explicitly selected this model. Do not request model churn when capability is known.

1. Fix the scope

Prefer the caller's supplied scope. Otherwise identify the repository and actual default branch from local repository policy or origin/HEAD; never assume a literal main. Resolve the comparison base to one full SHA before collecting changes. Missing or ambiguous scope requires clarification, not a guessed nearby task or branch. On trunk, use an explicit base when committed work is intended.

Read the full file on GitHub · 145 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 2d ago Changed · -138 lines · -43 tokens per session f89fbf7c94af
  2. 10d ago First seen · 283 lines · 82 tokens per session scan A 5fac601049dc

Subscribe to this mod's changes

pedantic-review is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 1,643 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.