Darwin Skill Optimizer
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
A skill your agent uses when the strategist drafts per-issue graded checks after decomposition and before builder dispatch.
Install Frozen Checks
$ npx skills add DanMcInerney/architect-loop --skill frozen-checks -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install DanMcInerney/architect-loop frozen-checks --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/DanMcInerney/architect-loop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/frozen-checks .claude/skills/frozen-checks && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "frozen-checks" agent skill from https://github.com/DanMcInerney/architect-loop/tree/main/skills/frozen-checks into .claude/skills/frozen-checks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frozen-checks", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/DanMcInerney/architect-loop/tree/main/skills/frozen-checksType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add DanMcInerney/architect-loop --skill frozen-checks -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install DanMcInerney/architect-loop frozen-checks --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DanMcInerney/architect-loop.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/frozen-checks .agents/skills/frozen-checks && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "frozen-checks" agent skill from https://github.com/DanMcInerney/architect-loop/tree/main/skills/frozen-checks into .agents/skills/frozen-checks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frozen-checks", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add DanMcInerney/architect-loop --skill frozen-checks -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install DanMcInerney/architect-loop frozen-checks --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DanMcInerney/architect-loop.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/frozen-checks .cursor/skills/frozen-checks && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "frozen-checks" agent skill from https://github.com/DanMcInerney/architect-loop/tree/main/skills/frozen-checks into .cursor/skills/frozen-checks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frozen-checks", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/DanMcInerney/architect-loop.git --path skills/frozen-checks--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add DanMcInerney/architect-loop --skill frozen-checks -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install DanMcInerney/architect-loop frozen-checks --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DanMcInerney/architect-loop.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/frozen-checks .gemini/skills/frozen-checks && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "frozen-checks" agent skill from https://github.com/DanMcInerney/architect-loop/tree/main/skills/frozen-checks into .gemini/skills/frozen-checks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frozen-checks", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install DanMcInerney/architect-loop frozen-checksInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add DanMcInerney/architect-loop --skill frozen-checks -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/DanMcInerney/architect-loop.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/frozen-checks .github/skills/frozen-checks && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "frozen-checks" agent skill from https://github.com/DanMcInerney/architect-loop/tree/main/skills/frozen-checks into .github/skills/frozen-checks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frozen-checks", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add DanMcInerney/architect-loop --skill frozen-checks -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install DanMcInerney/architect-loop frozen-checks --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DanMcInerney/architect-loop.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/frozen-checks .opencode/skills/frozen-checks && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "frozen-checks" agent skill from https://github.com/DanMcInerney/architect-loop/tree/main/skills/frozen-checks into .opencode/skills/frozen-checks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "frozen-checks", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
frozen-checks- GitHub stars
- 626
- Token cost
- ~816 tokens
- SKILL.md length
- 466 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when the strategist drafts per-issue graded checks after decomposition and before builder dispatch.
- The strategist drafts per-issue graded checks after decomposition and before builder dispatch
- SKILL.md covers RUN grammar, Falsifiable and atomic, Dependency surface and Freeze protocol, plus 1 more section
- Calls git
What it does
Frozen Checks is an agent skill from DanMcInerney/architect-loop. Use when the strategist drafts per-issue graded checks after decomposition and before builder dispatch. Produces one check file per issue at docs/checks/<run/<slice.md, frozen in git, read-only after.
Its SKILL.md is about 820 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows. It works with Git. The repository describes itself as: Super optimized /goal loop. Massive token savings and higher quality. Smart model designs and reviews, cheaper model builds.. The licence is MIT.
When your agent uses it
- The strategist drafts per-issue graded checks after decomposition and before builder dispatch
Example prompts
- “/frozen-checks”
What it can do on your machine
Read from SKILL.md and the folder at commit 28dca7d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Frozen Checks loads about 816 tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 466 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from DanMcInerney/architect-loop at commit 28dca7d, republished under its MIT licence (© DanMcInerney). 466 words, ~816 tokens.
Download SKILL.mdSave it as
.claude/skills/frozen-checks/SKILL.md (or your agent's skills folder).- name
- frozen-checks
- description
- Use when the strategist drafts per-issue graded checks after decomposition and before builder dispatch. Produces one check file per issue at `docs/checks/<run>/<slice>.md`, frozen in git, read-only after.
Frozen checks
One check file per issue, at docs/checks/<run>/<slice>.md. Open it with
purpose, a spec pointer, and a fix contract stating what a failure means and
which file to fix — that header is the closing review's entire intent context
for the issue. Write for a reader with no other memory of this run, in the
codebase-design vocabulary (skills/codebase-design/SKILL.md).
RUN grammar
Normative from the shipped runner, skills/architect/check-runner.ps1; cite
it, do not restate it divergently from skills/architect/dispatch.md's
## Check-runner dispatch. A graded item is exactly:
- RUN: `command` -> exit:<n> with optional trailing match:"<substring>".
match: is a fixed, case-sensitive stdout substring — never a regex. A RUN
item without an -> exit:<n> expectation makes the runner exit 5 with no
partial evidence kept; that is a check defect, not a builder defect. Every
other line — rationale, judge-only intent items — is read by the closing
review and the orchestrator, never graded by the runner.
Falsifiable and atomic
Each RUN item asserts exactly one falsifiable fact. Run every draft command against the current tree before freezing; a check that cannot fail is not a check.
Attack-list, run before freeze:
- Repo-name grep collisions — a pattern that matches unrelated hits because it contains the repo's own name.
- Self-matching — a pattern that matches the check file itself, not just the intended target.
git grepis blind to a builder's untracked new files in a worktree that hasn't staged them; use filesystemgrep/testthere instead.- New artifact paths — run
git check-ignore <path>; a gitignored path never gets graded no matter what the check says.
Show full SKILL.md (215 more words)Show less
Dependency surface
A RUN command's dependency set — the test files, validators, and scripts it executes — is part of the check's enforcement surface: agents that game a check edit the test, not the criteria file. Name that set in the check header. Decomposition keeps those files out of MAY TOUCH by default; when an issue legitimately owns one (a job writing the tests a RUN item runs), every builder edit to it must be disclosed in the job report, and the orchestrator re-verifies intent before trusting a green — the edited dependency must still fail a known-bad input.
Freeze protocol
All check files for a run commit to the factory branch before any builder is
dispatched; record the freeze SHA on the tracking issue.
After that commit, everything under docs/checks/ is read-only to every
builder and reviewer — an edit there is an automatic FAIL regardless of the
rest of the job report. An intent change discovered after freeze is a
ruling: it goes in the run's rulings file, never a rewrite of the frozen
check.
Duration hints
An issue or check file may note a duration hint in prose (e.g. "full suite ~20m") so a monitor doesn't mistake legitimate long work for a stall. A hint is informative only — never a kill ceiling, never a RUN expectation.
© DanMcInerney, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/frozen-checks of DanMcInerney/architect-loop.
Open the folder on GitHubat commit 28dca7d
Compare with similar skills
Frozen Checks next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Frozen Checks this skillDanMcInerney/architect-loop | 626 | — | ~816 | Automated safety check: Pass | MIT | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| CodeGraph Agent Evalcolbymchenry/codegraph | 74k | — | ~950 | Automated safety check: Pass | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| Beads Task Memorygastownhall/beads | 28k | — | ~1.2k | Automated safety check: Pass | MIT |
Similar skills
CodeGraph Agent Eval
colbymchenry/codegraph
Benchmarks how much CodeGraph helps a coding agent on a real repository, comparing runs with and without it for a chosen local or published version.
Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
Beads Task Memory
gastownhall/beads
Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.
Session History Search
slopus/happy
Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.
More from DanMcInerney/architect-loop
All 11 skills in this repoArchitect Research
DanMcInerney/architect-loop
A skill your agent uses when the user asks for discovery-scale research that informs a decision: brainstorming a project or feature, choosing a technology, or requests like "research X", "what's the…
Adversarial Review
DanMcInerney/architect-loop
A skill your agent uses when the architect factory orchestrator dispatches a fresh strategist subagent to harden a draft spec: falsify it with file:line evidence, fold the surviving findings into a…
Architect
DanMcInerney/architect-loop
A skill your agent uses when the user asks to architect, run or continue the autonomous software factory, turn a goal into a hardened tracker issue plan, dispatch builder jobs, grade finished work…
Architect Fast
DanMcInerney/architect-loop
A skill your agent uses when the user asks to architect-fast a change, run the light factory lane, or factory-build a small goal — a few files, roughly one sitting, at most ~3 parallel issues — into…
Final Review
DanMcInerney/architect-loop
A skill your agent uses for the closing whole-run review in the architect factory — the only model review in the loop: dispatched by the orchestrator, at finish, to one fresh strategist subagent…
TDD
DanMcInerney/architect-loop
Test-driven development for factory builders. An agent skill from DanMcInerney/architect-loop.
Related
Works with
Categories
Questions about Frozen Checks
What does Frozen Checks do?
A skill your agent uses when the strategist drafts per-issue graded checks after decomposition and before builder dispatch. Frozen Checks is an agent skill from DanMcInerney/architect-loop. Use when the strategist drafts per-issue graded checks after decomposition and before builder dispatch.
When should I use Frozen Checks?
Frozen Checks fits situations like: the strategist drafts per-issue graded checks after decomposition and before builder dispatch.
How do I install Frozen Checks in Claude Code?
Run `npx skills add DanMcInerney/architect-loop --skill frozen-checks -a claude-code`. Or copy the skill folder (skills/frozen-checks in DanMcInerney/architect-loop) into .claude/skills/frozen-checks in your project. Claude Code loads it when a task matches its description.
How do I install Frozen Checks in Codex?
Run `npx skills add DanMcInerney/architect-loop --skill frozen-checks -a codex`. Or copy the skill folder (skills/frozen-checks in DanMcInerney/architect-loop) into .agents/skills/frozen-checks in your project. Codex loads it when a task matches its description.
Can I use Frozen Checks in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DanMcInerney/architect-loop --skill frozen-checks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/frozen-checks, .gemini/skills/frozen-checks, .github/skills/frozen-checks and .opencode/skills/frozen-checks in your project.
What does Frozen Checks need to run?
Going by SKILL.md and its folder, Frozen Checks needs the command-line tools its instructions call (git).
Does Frozen Checks access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Frozen Checks safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Frozen Checks use?
Frozen Checks is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Frozen Checks use?
About 816 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Frozen Checks?
Skills that share tags, products or a category with Frozen Checks: Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars), CodeGraph Agent Eval (colbymchenry/codegraph, 74k stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars) and O2 Review Loop (openobserve/openobserve, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Frozen Checks?
DanMcInerney (a GitHub user) maintains it in DanMcInerney/architect-loop, which has 626 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 13, 2026.
Source: DanMcInerney/architect-loop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.