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 flurdy/agent-skills --skill pedantic-reviewgit clone --depth 1 https://github.com/flurdy/agent-skillsWrote 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/flurdy/agent-skills/pedantic-review)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.01643 |
| Opus 5 | $0.00019 | $0.00822 |
| Sonnet 5 | $0.00008 | $0.00329 |
| Haiku 4.5 | $0.00004 | $0.00164 |
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.
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 — 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.
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.
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 Changed · -138 lines · -43 tokens per session f89fbf7c94af
- 10d ago First seen · 283 lines · 82 tokens per session scan A 5fac601049dc
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…