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/commands/oborchers/fractional-cto/guidelines-review)<a href="https://agentmods.dev/commands/oborchers/fractional-cto/guidelines-review"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/guidelines-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/commands/oborchers/fractional-cto/guidelines-review"><img src="https://agentmods.dev/badge/commands/oborchers/fractional-cto/guidelines-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 | $0.00019 | $0.00606 |
| Opus 5.5 | $0.00008 | $0.00242 |
| Sonnet 5.5 | $0.00004 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
guidelines-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 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.
What it actually says
Scan the repository for CLAUDE.md files and audit code compliance against the project's own documented guidelines.
Follow this process:
-
Discover all CLAUDE.md files: Use Glob with
**/CLAUDE.mdto find every CLAUDE.md file in the repository (or the scope provided as argument). -
Map the inheritance hierarchy: Order the files from root to deepest nesting. Understand which directories each file's guidelines apply to.
-
Read and parse each CLAUDE.md: For each file:
- Read the full content
- Distinguish enforceable guidelines (naming rules, patterns, conventions, architecture boundaries) from informational content (build commands, project overview, architecture descriptions)
- Note the scope: what directories and files does this CLAUDE.md govern?
-
Invoke the guidelines-compliance skill: Use
Skill("pedantic-coder:guidelines-compliance")to load the full compliance checking methodology. -
For each CLAUDE.md scope, sample and check files:
- Select 3-5 representative files within each CLAUDE.md's scope
- For each file, collect ALL applicable guidelines (walk up the ancestor chain)
- Check the file against every applicable guideline
- Record violations with the specific CLAUDE.md file and quoted rule
-
Check for systemic patterns:
- Are there guidelines that are widely ignored? (rule exists but nobody follows it)
- Are there guidelines that conflict between levels? (parent says X, child says Y)
- Are there stale guidelines? (reference patterns, files, or commands that no longer exist)
-
Report findings in this structure:
CLAUDE.md Hierarchy
- List all CLAUDE.md files found with their scope
Compliance by Scope
For each CLAUDE.md:
- Guideline: [quoted rule]
- Status: Compliant / Partially violated / Widely violated
- Evidence: file:line references for violations
- Fix: what to change (in code or in the guideline)
Conflicts
- Parent/child guideline contradictions
Stale Guidelines
- Rules that reference nonexistent patterns, files, or commands
Summary
- Total guidelines found: N
- Fully compliant: X
- Violated: Y
- Stale: Z
- Verdict: Are the project's own rules being followed?
Focus on substance over style. The goal is to answer: "Does this codebase follow its own rules?" If not, either the code or the rules need to change.
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 · 59 lines · 19 tokens per session scan A 2bfc4744fbb7
guidelines-review is a command published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 19 tokens to every session and 606 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
Other commands, from other repositories
refactor
Systematic code refactoring with smart scope detection.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.