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 lukas-grigis/ralphctl --skill ralphctl-iterative-reviewgit clone --depth 1 https://github.com/lukas-grigis/ralphctlWrote 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/lukas-grigis/ralphctl/ralphctl-iterative-review)<a href="https://agentmods.dev/skills/lukas-grigis/ralphctl/ralphctl-iterative-review"><img src="https://agentmods.dev/badge/skills/lukas-grigis/ralphctl/ralphctl-iterative-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/lukas-grigis/ralphctl/ralphctl-iterative-review"><img src="https://agentmods.dev/badge/skills/lukas-grigis/ralphctl/ralphctl-iterative-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 | $0.00073 | $0.00772 |
| Opus 5 | $0.00036 | $0.00386 |
| Sonnet 5 | $0.00015 | $0.00154 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
ralphctl-iterative-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 9d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iterative Review
Concept
from SPDD (Zhang & Xia, martinfowler.com) — "Iterative Review". Adapted for ralphctl's three phases.
One-shot generation looks fast and is slow. The cheap review you skipped at iteration N becomes the expensive unwind at iteration N+5, when a regression that lived undetected through five steps surfaces only at the post-task gate. Catching a problem at the seam between two changes is cheap; catching it at the end of a 200-line diff is not. The harness's check gate, the evaluator, and the review prompts are this loop in deployed form — but the same posture also belongs inside each phase's work.
When this applies
- Refine — re-read the drafted criteria once against the ticket before sending. Strike duplicates; tighten "should" / "ideally" into checkable predicates. Cheap to do here, expensive once planning splits tasks against the unclear version.
- Plan — re-read the generated task list against the requirements. Are the tasks independently shippable? Do dependencies match the actual data flow? Reorder, merge, or drop before importing.
- Execute — run the project's check gate (lint, typecheck, tests) after each meaningful change, not
after the whole diff. Re-read your own diff once before signalling
<task-complete>. You are the cheapest reviewer the change ever gets.
What to do
- Run the cheapest check first, often. Lint, typecheck, narrow test runs — not the full suite — after each meaningful change. The point is to catch the regression at the seam, not to certify completion.
- Re-read your own output once before submitting. Whether it is criteria, tasks, or a diff, the second read catches what the first one missed. Cheap.
- Treat the check gate as a loop, not a finish line. A failing gate is feedback, not a verdict. Apply the fix and re-run; do not signal completion against a red gate.
- When a fix attempt repeats the same failure, escalate rather than retry. Two iterations of the same
error is a plateau — the next fix is a guess. Surface the blocker via
<task-blocked>or<note>rather than burning the budget.
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.
- 9d ago First seen · 52 lines · 73 tokens per session scan A 6b3d9091259d
ralphctl-iterative-review is a skill published in the GitHub repository lukas-grigis/ralphctl (23 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 772 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
My Skill
Content here.
atomic-visual-options
Planning-phase visual comparison aid. Renders 2-4 side-by-side variants per decision dimension as a single throwaway, self-contained HTML file and captures the user's pick as typed terminal codes (e.g. "A2 B3"). Auto-fires on phrases like "show me a few options", "mock up some variants", "let me see this side by…
atomic-wiki
Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the block in /.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via atomic wiki bucket add rather than a…
atomic-review
Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.
atomic-verify
Evidence-before-claim gate. Auto-triggers when Claude is about to claim "done", "fixed", "passing", "complete", "ready to merge", "looks good", "should work", "should pass", "green", or any synonym. Iron rule: no completion claim without a fresh verification command run in this turn. Explicit invocation…