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 EricTechPro/startup-claude-skills --skill review-fixgit clone --depth 1 https://github.com/EricTechPro/startup-claude-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/erictechpro/startup-claude-skills/review-fix)<a href="https://agentmods.dev/skills/erictechpro/startup-claude-skills/review-fix"><img src="https://agentmods.dev/badge/skills/erictechpro/startup-claude-skills/review-fix/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/erictechpro/startup-claude-skills/review-fix"><img src="https://agentmods.dev/badge/skills/erictechpro/startup-claude-skills/review-fix.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 | $0.00046 | $0.04505 |
| Opus 5.5 | $0.00018 | $0.01802 |
| Sonnet 5.5 | $0.00009 | $0.00901 |
| Haiku 4.5 | $0.00005 | $0.00451 |
Grade A, and why
review-fix 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 1mo 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 — 694 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review-Fix Loop
Orchestrate an automated review-fix cycle that iterates until your code is clean. Each iteration spawns fresh sub-agents with full 200k context windows, fixes quick-fix items automatically, and accumulates strategic items for user decision at the end.
When to Use This Skill
- Before creating a PR - Get comprehensive feedback AND automatic fixes
- After major refactoring - Ensure quality across multiple review cycles
- When you want hands-off improvement - Let the loop fix issues automatically
- For iterative polish - Run until no quick-fix items remain
Parameters
| Parameter | Default | Description |
|---|---|---|
max-iterations |
3 | Maximum review-fix cycles before stopping |
auto-commit |
true | Create a commit after each fix cycle |
skip-strategic |
false | Skip strategic item questions at the end |
base-commit |
main |
Commit/branch to compare against (e.g., abc123, HEAD~5, develop) |
Architecture
ORCHESTRATOR (main session - manages state only)
|
+-- REVIEW PHASE (8 parallel sub-agents, each with fresh 200k context)
| +-- premium-ux-designer
| +-- product-strategy-advisor
| +-- general-purpose
| +-- system-architect
| +-- code-refactorer
| +-- code-refactorer
| +-- Explore (reusable components)
| +-- Explore (dead code)
|
+-- FIX PHASE (single sub-agent, fresh 200k context)
| +-- General agent with fix prompt + file context
|
+-- STATE FILE (.review-fix/state.json)
+-- Tracks iterations, strategic items, fixed items, commits
Workflow
Step 0: Initialize State
Create/update the state file at .review-fix/state.json:
{
"iteration": 1,
"maxIterations": 3,
"baseCommit": "main",
"strategicItems": [],
"fixedItems": [],
"commits": [],
"status": "in_progress",
"startedAt": "2025-01-18T10:00:00Z",
"branchName": "feature/example"
}
Step 1: Extract Branch Context
# Get current branch name
BRANCH=$(git branch --show-current)
# Get base commit (from parameter or default to main)
BASE_COMMIT="${base_commit:-main}"
# Validate base commit exists
if ! git rev-parse "$BASE_COMMIT" >/dev/null 2>&1; then
# Fallback to master if main doesn't exist and no custom base provided
if [ "$BASE_COMMIT" = "main" ]; then
BASE_COMMIT="master"
fi
fi
# Get diff stats against base commit
git diff --stat "$BASE_COMMIT"..HEAD
# Get list of changed files
git diff --name-only "$BASE_COMMIT"..HEAD
# Get commit messages since base
git log --oneline "$BASE_COMMIT"..HEAD
# Get detailed diff for context
git diff "$BASE_COMMIT"..HEAD --no-color
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.
- 1mo ago First seen · 694 lines · 46 tokens per session scan A 7dc3196e0e25
review-fix is a skill published in the GitHub repository EricTechPro/startup-claude-skills (60 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 4,505 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…