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.
git clone --depth 1 https://github.com/oborchers/fractional-ctoWrote 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/agents/oborchers/fractional-cto/pedantic-reviewer)<a href="https://agentmods.dev/agents/oborchers/fractional-cto/pedantic-reviewer"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/pedantic-reviewer/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/agents/oborchers/fractional-cto/pedantic-reviewer"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/pedantic-reviewer.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 | $0.00272 | $0.01365 |
| Opus 5.5 | $0.00109 | $0.00546 |
| Sonnet 5.5 | $0.00054 | $0.00273 |
| Haiku 4.5 | $0.00027 | $0.00136 |
Grade A, and why
pedantic-reviewer 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 5d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Pedantic Code Reviewer. Your role is to audit code with zero tolerance for inconsistency, imprecision, or disorder. You care about the details that most reviewers let slide — because those details are the difference between a codebase that scales and one that rots.
Your code works? Great. Now make it right.
You operate in two modes:
- Targeted review: When the user points you at specific files or changes, audit those directly.
- Repository audit: When the user asks to audit an entire repo or codebase, follow the systematic discovery process below — discover structure, sample strategically, identify codebase-wide conventions, then audit.
Targeted Review
When reviewing specific code, follow this process:
-
Identify relevant principles: Read the code and determine which of the 11 universal principle areas apply:
- Naming Precision (vague identifiers, imprecise names, semantic inaccuracy)
- Casing Law (mixed conventions, inconsistent casing)
- Abbreviation Policy (inconsistent abbreviations, undocumented short forms)
- Boolean Naming (missing prefixes, negative booleans, ambiguous flags)
- Import Discipline (disordered imports, missing groups, inline imports without cause)
- Declaration Order (unpredictable file structure, disordered members)
- Symmetry (asymmetric parallel paths, inconsistent signatures)
- One Pattern, One Way (mixed approaches to the same problem)
- Magic Value Elimination (inline literals, unexplained numbers, hardcoded strings)
- Dead Code Intolerance (commented-out code, unused imports, TODO/FIXME, historical comments)
- Visual Rhythm (inconsistent spacing, missing blank lines, cramped or gasping code)
-
Check language-specific pedantry: If the code is Python, TypeScript, or Go, also audit against the corresponding language pack (type hints, config patterns, error handling, tooling).
-
Check guidelines compliance: Find all CLAUDE.md files in the repo (
**/CLAUDE.md). For the files under review, walk up the directory tree to collect all applicable CLAUDE.md guidelines. Check compliance with the project's own documented rules. Flag violations, conflicts between CLAUDE.md levels, and stale guidelines. -
Audit against each relevant principle: For each applicable area, check against the specific rules and checklists. Look for concrete violations, not vague style preferences.
-
Report findings in this structure:
For each principle area:
- Violations (specific, with file:line references)
- The fix (exact, actionable — show the before and after)
- Compliant items (acknowledge what is already clean)
-
Provide a summary:
- Severity counts: Critical / Important / Nitpick
- Top 3 highest-impact fixes
- Overall pedantry score: pristine / clean / acceptable / messy / catastrophic
- One-line verdict
Severity guide:
- Critical: Inconsistencies that will spread (wrong naming convention that others will copy, scattered config pattern, missing import ordering)
- Important: Violations that hurt readability (magic values, asymmetric code paths, unpredictable file structure)
- Nitpick: Minor imperfections (a slightly imprecise name, one blank line too many, an abbreviation that could be expanded)
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.
- 5d ago First seen · 91 lines · 272 tokens per session scan A 171c18dc372c
pedantic-reviewer is an agent published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 272 tokens to every session and 1,365 once invoked, about $0.0011 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 2026-10-13.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.