claude

code-improver

Improves code targets — skills, plugins, or a branch's changes — through an autonomous review-and-fix workflow with a pluggable reviewer (any installed skill or agent), a cross-round findings ledger, oscillation escalation, and a mechanical scope guard.

8,166 on GitHubby Paweł Płatekv1.0.3CC-BY-SA-4.0updated today
/

Plugin code-improver from marketplace trailofbits in trailofbits/skills. Commands read from the repo's manifest — today.

What it installs

Skills (3)

  • code-improver

    Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user names: any installed skill or agent. Keeps a cross-round findings ledger, escalates when fixes stop converging, and guards scope mechanically. Use when asked to

  • pr-improver

    Runs an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean, scoped mechanically to the directories the branch touched. Reviews are performed by an installed PR-review skill (default: pr-review-toolkit's review-pr). Use to fix review findin

  • skill-improver

    Runs an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cross-round findings ledger, escalation when fixes stop converging, and a mechanical scope guard. Reviews are performed by the plugin-dev skill-reviewer agent. Use to fix skill quality

Subagents (1)

  • fixer

    Applies fixes for the blocking findings dispatched by the /code-improver:improve workflow and returns one verdict per finding (fixed, rejected, or deferred) under a hard scope and git-safety contract. Dispatched by the workflow only; not for ad-hoc editing.

View source on GitHub

More from trailofbits/skills

All 47 plugins →

trailmark

claude

Builds source and binary code graphs for security analysis, taint modeling with native analyzers, context slicing, mutation testing, cryptographic protocol modeling, finding triage, and variant analysis.

15 skills · 1 agent

8,166

testing-handbook-skills

claude

Skills from the Trail of Bits Application Security Testing Handbook (appsec.guide)

15 skills

8,166

zeroize-audit

claude

Detects missing or compiler-optimized zeroization of sensitive data with assembly and control-flow analysis

1 skill · 11 agents · 1 MCP server

8,166

building-secure-contracts

claude

Comprehensive smart contract security toolkit based on Trail of Bits' Building Secure Contracts framework. Includes vulnerability scanners for 6 blockchains and 5 development guideline assistants.

11 skills

8,166

regression-hunt

claude

Agent-orchestrated skills for finding, reproducing and adjudicating regressions in PRs or commits.

7 skills

8,166

dimensional-analysis

claude

Audits code for unit and decimal-scaling bugs and annotates it with dimensional comments recording the units of each value. Use when someone asks to audit or review code for unit confusion, decimals or scaling mismatches, WAD/RAY scale errors, or the wrong token's decimals; to annotate units in a codebase; or to perform a dimensional analysis of a DeFi protocol, offchain code, or other arithmetic-heavy codebase. Catches formulas that combine values carrying different units or scales.

1 skill · 5 agents

8,166

Maintain code-improver?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins47 plugins