Claude-Code-Game-Studios
Turn Claude Code into a full game dev studio — 49 AI agents, 75 workflow skills, and a complete coordination system mirroring real studio hierarchy.
- 41k
- Shell
- MIT
- 13 d ago
An eraser against LLM-induced code & document entropy. Support if you like it!
Repo skymanbp/CodeEraser, read from GitHub 3 d ago. skymanbp has not joined Take My Repo.
skymanbp/CodeEraser is a public repo on GitHub by skymanbp. An eraser against LLM-induced code & document entropy. Support if you like it! It declares the Apache-2.0 license on GitHub. It is written mainly in Haskell, has 15 stars and last changed on 2026-11-17. Nobody has reviewed it on Take My Repo yet, which says nothing about its quality. Read from GitHub on 2026-11-19.
In the maintainer's words. Shown from GitHub; Take My Repo does not keep a copy.
· English | 中文
CodeEraser keeps an agent-written repo small and clean: a write that duplicates code or bloats a file is refused before it lands.
LLM-assisted codebases drift the same way: the same function written twice, the same paragraph pasted into three files, files that only grow. CodeEraser refuses the write that would do that, before it reaches disk, with no model in the loop.
[guard] mode = "deny" the Stop audit refuses the turn and ce precommit the commit (by default both record and do not refuse).Judges Python, TypeScript/TSX, Rust, Go, Haskell, C, C++, Java, Lua, R, Markdown and HTML (thirteen language codes, twelve tree-sitter grammars); JS, CSS, Vue, Svelte, shell and YAML files for size only; .txt for documentation duplication only.
Runs as CLI · GUI (eleven screens) · Claude Code plugin (four hooks, one skill, one command, twenty-one read-only MCP tools) · pre-commit · CI.
| Without CodeEraser | With CodeEraser | |
|---|---|---|
| writes refused before they reached disk | 0 | 2 |
| duplicate clone blocks left behind | 4 | 0 |
| duplicated doc segments | 1 | 0 |
| removals still owed | 1 | 0 |
| check score | 752 | 1000 |
One seven-step task, two identical copies of the seed; the only variable is whether CodeEraser is in the loop — the write-time guard, the Stop audit, and, once the audit refuses, the eraser acting on its own plan. Both runs still end red — not on the same things.
A scripted agent replays one seven-step task (discounts, a compact report, CSV and JSON output, money formatting) on demo/seed, a small invoicing service, once without CodeEraser and once with it. Every number above and every refusal below is ce's verbatim output.
A copied helper, refused before the file exists. Move 1 of the run above, on its own. The reason names the region the content duplicates and the ordering that would pass, so the refusal is actionable rather than a veto.
$ Write invoicer/discount.py
✗ ce: content for <work>/invoicer/discount.py duplicates 1 indexed region(s): invoicer/money.py:6-18 (80 tokens). Reuse the existing implementation instead of re-writing it. Moving it? Trim the source region first: the probe verifies against the current tree, and the same write then passes.
One line, two mouths. ce.toml puts invoicer/** on file_lines_fail = 40. The write-time guard refuses the write that would cross it, and ce scan grades the same tree against the same number — one declaration, read by the hook and by CI.
$ Write invoicer/invoice.py
✗ ce: <work>/invoicer/invoice.py is already past the hard budget of 40 at 51 lines; this write grows it to 93 (plan §4.1). A write that keeps or shrinks it passes: split it step by step.
$ ce scan .
FAIL invoicer/invoice.py:1 file-lines = 51 (limit 40) [invoicer/invoice.py]
warn invoicer/report.py:1 file-lines = 35 (limit 30) [invoicer/report.py]
scanned 9 files / 19 functions — 1 warn, 1 fail -> FAIL (failed: hard_line)
The full table, both transcripts and the JSON behind them are in demo/README.md, replayed byte for byte in CI; the first real interception is recorded in T1-INTERCEPT. The precision and recall points are frozen with their evaluation ledgers (EVAL-SET, EVAL-SET-LANGS).
Zoom and pan this diagram at codeeraser.dev/how/#verdict.
[score.weights] deadcode names it), held by the ADR-006 shrink-only ratchet (growth needs max(+2 %, +10 lines) or a named re-establish).ce → ce-core pipe, and the core opens no file.The rest — same-role advice, Datalog queries and rules, intra-function dead code, merge suggestions, architecture, structure axes, tombstone residue, erase — is on codeeraser.dev/how and in the methodology booklets.
ce and the ce-core judgment core; the Windows installer runs ce setup (AppImage / dmg users run it once), which wires Claude Code. The fifteen artifacts are unsigned by decision; verify with sha256sum -c --ignore-missing SHA256SUMS.brew install skymanbp/codeeraser/codeeraser; winget install skymanbp.CodeEraser once winget-pkgs merges./plugin marketplace add skymanbp/CodeEraser@release, then /plugin install codeeraser@codeeraser.ce and ce-core side by side on PATH; cargo install codeeraser builds ce only, so take ce-core from a release or build it with GHC 9.14.1 + cabal; ce finds the core as CE_CORE_BIN → a ce-core sibling → PATH, and --core <path> wins.ce update checks the latest release against its two-phase pins and --yes replaces the binaries (RELEASE).| Command | What it reports / judges |
|---|---|
ce scan / ce dedup |
size and complexity metrics; T1/T2 clone blocks against the budget |
ce clone / ce docdup |
T3 near-miss clones; documentation duplication |
ce graph / ce deadcode |
reference sites and mentions; liveness verdicts |
ce churn / ce join / ce trend |
git-window churn; the three-signal join; score trajectory |
ce similar |
same-role units, ranked by the core; advice only |
ce query / ce rules |
Datalog over the index's facts; rules judged as a gate |
ce flow |
dead code inside functions, from the control-flow graph |
ce merge |
how a clone group would fold into one function; advice only |
ce arch |
directory layers, cycle cuts, clusters, change impact; advice only |
ce structure |
eight structure axes and split pricing |
ce check / ce baseline |
the ratchet and score floor, seven named fail conditions |
ce erase |
the deterministic two-phase eraser; dry run by default |
ce update |
latest release vs this build; --yes installs it |
ce doctor / ce setup / ce eject / ce mcp |
machine state; Claude Code wiring; uninstall; the MCP server |
Output is English by default and Chinese under --lang zh, CE_LANG=zh or [ui] lang = "zh". [[rules.class]] in ce.toml gives one glob set its own lines and ratchet tolerance (ce.toml reference).
Every capability reaches the CLI, the GUI and the plugin with its MCP server, or is a named omission; the face_parity gate derives the sets from the code.
| capability | report document (core catalogue) | CLI | GUI (screen · commands) | plugin (hooks · MCP · commands · skills) |
|---|---|---|---|---|
| size / complexity / readability metrics | scan |
ce scan |
reports, scan_report |
MCP scan |
| T1/T2 clone blocks | dedup |
ce dedup |
reports, candidates, dedup_report |
MCP check_duplication |
| T3 near-miss clones | clone |
ce clone |
reports, clone_report |
MCP clone |
| the unit universe T3 judges | clone-units |
ce clone --units |
reports, clone_report |
MCP clone |
| documentation duplication | docdup |
ce docdup |
reports, docdup_report |
MCP docdup |
| reference sites | sites |
ce graph --sites |
reports, sites_report |
MCP graph_sites |
| the mention universe | mentions |
ce graph --mentions |
— CLI only: the census behind the symbol advisory, which every face of deadcode carries |
— CLI only: the MCP deadcode tool carries the advisory the census feeds |
| liveness verdicts + symbol advisory | deadcode |
ce deadcode |
reports, deadcode_report |
MCP deadcode |
| graph screen (canvas + liveness) | graphscreen |
— GUI only: the canvas is a picture; the same judgment's CLI and MCP faces are deadcode |
graph, graphscreen_report |
— GUI only: the MCP face of the same judgment is deadcode |
| git-window churn | churn |
ce churn |
reports, churn_report |
MCP churn |
| three-signal join | join |
ce join |
candidates, join_report |
MCP join |
| tree-scale structure (split pricing) | structure |
ce structure |
structure, structure_report |
MCP structure |
| score trajectory | trend |
ce trend |
trend, trend_report |
MCP trend |
| score, ratchet and floor | check |
ce check |
score, check_report |
MCP check |
| same-role advisor (similar units, associative view) | similar |
ce similar |
similar, similar_report |
MCP similar_units |
| code query and architecture rules | query, rules |
ce query, ce query --prelude, ce rules |
query, query_report, query_prelude, rules_report |
MCP query, MCP rules |
| intra-function dead code (unreachable, dead stores, unused locals and parameters) | flow |
ce flow, ce flow --check |
reports, flow_report, flow_kinds |
MCP flow |
| clone merge suggestions (anti-unification) | merge |
ce merge |
reports, merge_report |
MCP merge_suggestions |
| architecture analysis (layers, cuts, clusters, impact) | arch |
ce arch |
reports, arch_report |
MCP architecture |
| baseline writes | — | ce baseline |
— CLI only: a machine surface never writes a baseline | — |
| erase plan | erase |
ce erase |
erase, erase_preview |
MCP erase, skill erase |
| erase apply | — | ce erase --apply |
erase, erase_apply |
— no MCP face: applying is a human act |
| erase audit log | erase-trail |
ce erase --log |
erase, erase_log_report |
MCP erase_log |
| machine state and guard-class tiers | — | ce doctor |
doctor, doctor_report |
MCP doctor |
| update check | — | ce update |
update, update_check |
MCP update_check, /codeeraser:update, hook SessionStart |
| update apply | — | ce update --yes |
update, update_apply |
— the plugin's copy is re-pinned by /plugin update codeeraser |
| write-time guard | — | ce probe --hook (guard · flow · tombstone) |
— hooks are the plugin's face; flow and tombstone judge the write inside the hook, so no report family of their own — their tiers ride every face's doctor | hook PreToolUse |
| asked-write settlement | — | ce settle --hook |
— hooks are the plugin's face | hook PostToolUse |
| stop audit / git hooks | — | ce audit --hook (guard · flow · tombstone), ce precommit (guard · flow · tombstone), ce commitmsg (guard · flow · tombstone) |
— hooks are the plugin's face; precommit and commitmsg are git's; tombstone judges the changeset inside them, its tier on every face's doctor | hook Stop |
| session health line | — | ce health --hook |
— hooks are the plugin's face | hook SessionStart |
| project daemon | — | ce daemon, ce ping |
— started lazily by every face | — |
| read-only report server | — | ce mcp |
— the plugin registers it | .mcp.json |
| uninstall | — | ce eject |
— CLI only | — |
| Claude Code wiring | — | ce setup, ce setup --unwire |
— CLI only: the Windows installer calls it, AppImage / dmg users run it once | — |
| root anchoring | — | — every command and hook anchors through root |
default_root, resolve_root |
— |
Zoom and pan this diagram at codeeraser.dev/#architecture.
ce-core, every judgment family. Tauri 2: the GUI over the same crate.PreToolUse shapes behaviour; it is not a security wall (shell writes bypass it; CI is the backstop, and the Stop audit too under [guard] mode = "deny"). The probe matches a write against the index as it stands and does not refresh it: a file created or changed outside Write/Edit (a shell command, an editor, git) becomes a duplicate source at the next whole run (ce dedup, the Stop audit). Hooks fail open on internal errors and on a hook envelope over 4 MiB (the largest writes pass unjudged), and record the degradation.
.txt by documentation duplication only; T4 clones are not promised.ce similar, ce merge and ce arch never fail a gate; a guard class stays observe until it has its own false-positive record.[score.weights] deadcode = 1 counts its lines as findings again.cognitive_fail defaults to 0 (complexity only warns), and ce structure has no score floor.require(prefix .. name), import("./lib/" + name)) or a star import whose __all__ is not all literal draws no edge for what it does not spell: the file stays unreferenced and its language cannot vouch for it. Unreferenced is not unused, so the default lists such a file and fails nothing; a project that wants new ones blocked declares [deadcode] block and commits a baseline. Nor is it a deletion licence: a file nothing references may still be run by name or found by a tool's convention (the eight conventions the dead-file exam passed, among them setup.py, Sphinx's conf.py, package-info.java and a Next.js app/ page, are entries; a convention the product does not list is not), so ce erase deletes no whole file and erases only byte-identical documentation spans. Entry points declared in setup.cfg or a non-root pyproject.toml are not read, and booklet 06 lists the other reference forms and entry families the graph does not read (a file reached only by include!, a script run by its path, a worker loaded by new URL(...), among others), each with its remedy: [graph] entry_globs, or ce:allow(deadcode) -- <why> in the file.ce setup wires nothing from an elevated account that is not the logged-in user (exit 13); judging this repository needs the cli/tests submodule seated.Scores are not comparable across a [[rules.class]] switch, across a named re-establish that moves softLine, or across these releases: v0.7.3 → v1.0.0, v1.2.0 → v1.3.0, v1.3.x → v1.4.0, v1.6.0 → v1.7.0, v1.7.4 → v1.8.0, v1.8.0 → v1.9.0 (1.9.1 and 1.9.2 are comparable with 1.9.0), v1.9.x → v1.10.0 (the score became the share of lines no finding names, and the unreferenced axis weighs 0 unless named; 1.10.1 is comparable with 1.10.0), v1.10.1 → v1.10.2 (Python docstrings give no clone token and are read past a leading comment; a docstring or a comment block, in any language, keeps the prose under a tilde title underline; 1.10.3 is comparable with 1.10.2); the reasons are in CHANGELOG.
Apache-2.0; see LICENSE. Third-party inventory in NOTICE (regenerated and gated in CI). The test suite lives in skymanbp/CodeEraser-tests; clone with --recurse-submodules. "CodeEraser"™ is a trademark of skymanbp; per Apache-2.0 §6 the license covers the code, not the name.
skymanbp/CodeEraser is a public repo on GitHub by skymanbp. An eraser against LLM-induced code & document entropy. Support if you like it!
It declares the Apache-2.0 license on GitHub.
Its maker tagged it for macOS and Windows. That is declared by the maker; Take My Repo has not tested it.
Open "Take it" on its page: Take My Repo writes an install plan for your machine and hands it to your AI agent (Claude Code, Codex or Cursor), which asks you before each step. Take My Repo has not tested it on any machine.
Its last change on GitHub was on 2026-11-17. GitHub counts 0 open issues and pull requests. Take My Repo does not judge from that whether it is maintained.
Nobody has reviewed it on Take My Repo yet, which says nothing about its quality.
Turn Claude Code into a full game dev studio — 49 AI agents, 75 workflow skills, and a complete coordination system mirroring real studio hierarchy.
Reverse engineer anything with agents, from app behavior down to native binaries.

Copy/paste detector for source code. 220+ languages, Rust engine, SARIF/HTML/badge reporters, GitHub Action, MCP server for AI agents.


The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
AI-assisted RAW photo developer: GPT vision advisor proposes an EditRecipe, a deterministic Rust engine renders it — Lightroom-compatible XMP sidecars, 24 RAW formats + baked images, measured (not guessed) Lightroom mask geometry, local GUI/web UI, AI denoise & segmentation sidecars
Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adversarial critique, and design-space exploration. 12 framings × hard-ban-on-incomplete-leaves × stable convergence.
Persistent memory for Claude Code. Survives compaction and session boundaries: anti-patch reconcile-on-write with LLM-judged de-duplication, a forced PROGRESS.md handoff, a live PLAN.md anchor with an enforced directive ledger, FTS5 search, MCP tools and a GUI. Pure stdlib Python, zero runtime dependencies.
Rules your coding agent physically cannot ignore. Claude Code hooks that DENY the tool call and BLOCK the reply - stopping reactive patches, guessed citations, and premature 'done' claims. Also works as an LLM-agnostic rule pack.
Claude Code plugin for scientific paper writing, source-traced review, and de-AI rewriting. 12 skills + 35 tools under one typed standard: non-waivable integrity blockers, zero-target L0 lexicon, ranked advisories, and explicit measurement states so missing calibration never reads as clean. Corpus-calibrated for ApJ/MNRAS/PRD/JCAP manuscripts.
Native-capability and interop floor for Haskell data science: runtime dynamic loading, Arrow C ABI + DLPack interop, ONNX Runtime inference, CBLAS/LAPACKE - zero build-time native deps
This page is also available as structured data, with the same sources and dates.
/api/v1/resources/gh/skymanbp/CodeEraserTake My Repo has not tested this on your machine. Requirements come from the project's own documentation.