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 salmundani/ralphex --skill ralphex-reviewgit clone --depth 1 https://github.com/salmundani/ralphexWrote 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/salmundani/ralphex/ralphex-review)<a href="https://agentmods.dev/skills/salmundani/ralphex/ralphex-review"><img src="https://agentmods.dev/badge/skills/salmundani/ralphex/ralphex-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/salmundani/ralphex/ralphex-review"><img src="https://agentmods.dev/badge/skills/salmundani/ralphex/ralphex-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 | $0.00017 | $0.01851 |
| Opus 5 | $0.00009 | $0.00925 |
| Sonnet 5 | $0.00003 | $0.00370 |
| Haiku 4.5 | $0.00002 | $0.00185 |
Grade A, and why
ralphex-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 11d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralphex Review: Iterative Code Review with Codex
Execute an iterative review loop where Codex reviews your existing code, you (Claude Code) filter the suggestions and implement fixes, then Codex reviews again. Loop until there is no relevant corrections to implement in Codex's review.
Step 1: Read Settings
- Generate a session ID by running
head -c 4 /dev/urandom | od -An -tx1 | tr -d ' \n'via Bash. Store the output assession_id. - Check if
.claude/ralphex.local.mdexists in the project root. - If it exists, read it and parse the YAML frontmatter to extract:
base_branch: The branch to diff against (default:main)codex_model: The Codex model to use (REQUIRED - if missing, ask the user)codex_reasoning_effort: Reasoning effort for Codex reviews (default:high)
- If the file does not exist, first run
command -v codexvia Bash. If the command exits with a non-zero status (codex not found), inform the user: "Codex CLI is not installed. Install it from https://github.com/openai/codex and try again." and stop. Otherwise, ask the user:- What base branch to diff against (suggest
main) - What Codex model to use (
gpt-5.4,gpt-5.4-mini,gpt-5.5) - What reasoning effort to use for reviews (suggest
high; valid values:low,medium,high,xhigh) Then create.claude/ralphex.local.mdwith their answers.\
- What base branch to diff against (suggest
- Check for uncommitted changes by running
git status. If there are uncommitted changes, useAskUserQuestionto present these options: a. Commit modified tracked files: Rungit add -uto stage all modified tracked files. Ask the user for a commit message, then commit with that message. b. Commit all changes (modified + untracked): Rungit add -Ato stage everything including untracked files. Ask the user for a commit message, then commit with that message. c. Stash changes: Generate a unique stash name by runningdate +%sand using"ralphex-review-stash-{timestamp}". Rungit stash push -m "ralphex-review-stash-{timestamp}". Store the full stash message for later cleanup. d. Cancel: Stop the review. - Resolve the review target: Run
git rev-parse --abbrev-ref HEADto get the current branch. Compute areview_targetvalue:- If the current branch is different from
base_branch, setreview_target=base_branch. - If the current branch equals
base_branch, check iforigin/{base_branch}exists by runninggit rev-parse --verify origin/{base_branch}. If it exists, setreview_target=origin/{base_branch}. If it does not exist, inform the user that there is no remote to compare against and stop. - Verify there is actually a diff by running
git diff --stat {review_target}...HEAD. If the diff is empty, inform the user there are no changes to review and stop.
- If the current branch is different from
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.
- 11d ago First seen · 130 lines · 17 tokens per session scan A 6e3976dd899e
ralphex-review is a skill published in the GitHub repository salmundani/ralphex (3 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 1,851 once invoked, about $0.0001 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
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
tech-lead
Channel operator (IRC handle @techlead) for the mARC agent team. Compiles chat demands into ready-to-execute work, records them on the GitHub Project board/Issues, and dispatches to specialists (@dev, @sre, @design, @sec, @rev, @research). Invoke with /tech-lead to turn discussion into tracked, delegated tasks.
init
Opt-in onboarding for the mARC agent team. Scaffolds a per-repo team binding so the team graduates from ephemeral session-memory to persistent, versioned config — without ever writing a file silently. Discovers the repo's org/repo/ project at runtime via gh, prefills {{ agentsdir }}/team.toml, and (optionally) a lean…
review
Run a full code review on current changes or specified files. Runs ruff lint, review-code agent, and security scan in sequence.
self-review
Surface the riskiest parts of the current diff so a reviewer knows where to look hardest — one inline pass on small diffs, one cold read on a cheaper model tier with in-session synthesis on substantial ones. INVOKE PROACTIVELY whenever a change is finished and about to be handed off, reviewed, or shipped. It points…