A well-documented, agent-navigable monorepo whose heavy media assets and unpruned file tree tax context windows.
last scored 2026-09-17 · both lenses
Readiness lenses
The same repo, two ways: how ready it is for an AI coding agent, and for a human newcomer. Switch lenses to see each one's score and checks.
How ready the repo is for an AI coding agent to read, build, and operate it.
81 / 10031 of 44 checks passed across 6 categories.
Machine Orientation
85Solid, explicit AGENTS.md and README make machine orientation straightforward.
The repository provides clear guidance via an informative README and an explicit AGENTS.md specifying build, dev, commit, and style conventions. Essential setup rules, lockfiles, and environment templates exist, clearing the Solid band (70-89).
Reproducible Setup
85Solid setup with pinned lockfiles and docker support, though root test invocation requires package-level routing.
The repository provides pinned dependencies (`bun.lock`), explicit package manager constraints (`packageManager: bun@1.3.14`), an environment example (`.env.example`), a Dockerfile, and robust CI workflows for testing and typechecking. However, root test invocation explicitly fails via script guard (`"test": "echo 'do not run tests from root' && exit 1"`), meaning agents must navigate package-specific test execution without centralized root wrappers. This clears the Solid band (70–89).
Code Navigability
82Well-organized monorepo workspaces and clear agent navigation guide make localization straightforward despite scale.
The repository is well-structured into conventional workspaces (`packages/*`) with clean module boundaries and robust guidelines in AGENTS.md, but spans 6,626 files with mixed typechecking strictness across packages. This places it solidly in the Solid band (70-89) as an agent can navigate core modules reliably with clear patterns.
Verification Surface
80Solid verification infrastructure with comprehensive CI and typechecking, though root test delegation requires workspace awareness.
The repository provides robust verification signals including extensive test suites, workflows (.github/workflows/test.yml, typecheck.yml), and explicit package scripts for linting (oxlint) and typechecking (bun turbo typecheck). However, the root package.json explicitly prevents running tests from the root (`echo 'do not run tests from root' && exit 1`), requiring agents to navigate workspace turbo commands or package subdirectories to execute checks. This clears the Solid band.
Agent Safety
85Solid agent safety hygiene with clear threat modeling, clean secret management, and explicit operational warnings.
The repository demonstrates solid agent safety with correct secret hygiene (env.example present, .gitignore covering secrets, zero secret-shaped hits) and explicit security guidelines in SECURITY.md detailing lack of sandboxing and server risks. Minor gaps include lack of an explicit trusted boundaries list for agent file access beyond standard config files, but overall safety practices are well established and verifiable.
Context Economy
60Massive file tree and heavy media artifacts create high noise that strains agent context windows.
Although the repo manages node_modules and build outputs via gitignore, it spans 6,626+ files across deeply nested mono-repo packages and artifact directories without clear `.gitignore` scopes or split submodules for auxiliary large media assets (like `artifacts/glm52-rise-video/out/`), overwhelming agent context windows. Essential guidelines exist (`AGENTS.md`, `.opencode/`), but navigating the immense raw file count without a curated map drops it into the Workable band.
Machine Orientation
6 checks passed4 problems found
- lowllms.txt present
An llms.txt is the emerging machine-orientation standard — a curated map for LLMs.
Fix: Add an llms.txt pointing at the key docs and entry points.
- lowTopics set
GitHub topics situate the repo's domain and stack for an agent at a glance.
Fix: Add a few GitHub topics describing the domain and stack.
- lowArchitecture doc
An ARCHITECTURE doc hands an agent the module map instead of making it infer one.
Fix: Add an ARCHITECTURE.md describing the major components and how they fit.
- lowExamples directory
An examples/ directory gives an agent runnable, copyable references for the API.
Fix: Add an examples/ directory with small, runnable usage samples.
- README present — An agent reconstructs what the repo is and how to work in it from the README first.
- Agent instructions file — AGENTS.md / CLAUDE.md is the direct, machine-read channel for entry points and conventions.
- Agent instructions stay lean — A bloated instructions file burns context and measurably hurts more than it helps.
- Repository description set — The one-line description is the fastest orientation signal an agent reads.
- README shows usage — A usage/example section tells an agent how the project is actually invoked.
- Contribution conventions are written down — A contributor guide is where an agent learns the branch, commit, and review conventions it must follow.
Reproducible Setup
6 checks passed1 problem found
- lowDev container
A .devcontainer gives an agent a one-command, fully-declared environment.
Fix: Add a .devcontainer so the toolchain is declared, not assumed.
- Lockfile committed — Without a lockfile two clones can resolve different dependency trees — the build isn't reproducible.
- Runtime / toolchain pinned — An unpinned runtime makes an agent guess the version a clean environment needs.
- Version pins are exact — A floating pin (a bare major, or a range) still drifts between installs.
- Env template present — A .env.example tells an agent which configuration keys it must supply to run.
- Container or dev-container — A Dockerfile / compose / devcontainer removes 'works on my machine' from setup.
- README documents setup — Explicit install/setup steps are what let an agent go from clone to running.
Code Navigability
2 checks passed3 problems found
- lowTypeScript strict mode on
Strict typing gives an agent typed signatures to anchor an edit on, not guesses.
Fix: Turn on `strict` in tsconfig.json.
- lowFormatter configured
A formatter config (Prettier/Biome/rustfmt/…) keeps style uniform across the tree.
Fix: Add a formatter (Prettier, Biome, rustfmt, …) and commit its config.
- lowTyped public API
A declared `types` entry gives an agent typed signatures to anchor an edit on.
Fix: Ship type declarations and point package.json `types`/`typings` at them.
- Conventional source layout — A recognised src/ · lib/ · app/ layout lets an agent localise code without spelunking.
- .editorconfig present — An .editorconfig keeps whitespace and encoding consistent, so diffs stay legible.
Verification Surface
5 checks passed2 problems found
- lowTask runner present
A Makefile / Taskfile / justfile gives an agent a single index of the project's commands.
Fix: Add a Makefile / Taskfile / justfile collecting the common commands.
- lowBuild command
A documented build command is the discoverable way for an agent to produce artifacts.
Fix: Add a `build` script that produces the distributable.
- Tests present — Runnable tests are the ground truth an agent checks its own edits against.
- Test command defined — A `test` script is the documented, discoverable way to run the suite.
- Lint command defined — A linter an agent can run catches a class of mistakes before they ship.
- CI configured — Readable CI is the feedback loop an agent reads to know what 'green' means here.
- Typecheck command — A typecheck script lets an agent catch type errors before they ship.
Agent Safety
9 checks passed2 problems found
- lowAutomated dependency updates
Dependabot / Renovate keeps dependencies patched without a human in the loop.
Fix: Enable Dependabot or Renovate.
- lowPolicy gives severity context
Severity judged against this system beats a generic rating an agent had to guess at.
Fix: Say in SECURITY.md how severity is judged here — what makes a finding critical for this system.
- No committed .env — A tracked real .env hands secrets to anything — including an agent — that reads the repo.
- No exposed secrets — Secret-shaped literals in tracked files are a live credential leak.
- .gitignore covers env files — An ignore rule for .env is what keeps the next careless commit from leaking secrets.
- CODEOWNERS present — CODEOWNERS marks the 'don't touch without review' zones an agent should respect.
- .gitignore present — A .gitignore is the first guard against an agent committing secrets or build junk.
- Security policy — A SECURITY.md is where an autonomous security agent reads this repo's rules before acting on it.
- Policy names the threat model — A scanning agent aims at what the repo says it is defending, and where untrusted input crosses in.
- Policy scopes what counts as a finding — With no reportable-finding bar and no out-of-scope list, an automated scan returns noise nobody triages.
- License makes the code reusable — Without a license an agent cannot safely copy, redistribute, or vendor any of this code.
Context Economy
3 checks passed1 problem found
- lowNo oversized source file
A single file in the hundreds of KB blows past an agent's effective context window.
Fix: Split the largest files along their natural seams.
- Dependencies not vendored in — A committed node_modules / vendor tree drowns the real signal an agent needs.
- Build output not committed — Generated dist/ · build/ output is noise an agent has to read past.
- Generated / vendored files marked — A .gitattributes linguist marker tells tools (and agents) what to skip.
How ready the repo is for a human newcomer to understand, set up, and contribute.
79 / 10022 of 33 checks passed across 6 categories.
First Impression
85Strong, purpose-driven README with clear installation and scope, missing only architectural internals.
The README provides a clear project purpose and visual preview at the top, accompanied by robust installation commands and agent explanations, clearing the Solid band (70–89). However, because it lacks dedicated architecture documentation or a structured project scope beyond basic usage links, it falls short of exemplary status.
Getting Running
75Solid setup instructions with bun and clear workflow commands, though lacking an explicit root env template.
The repository features clear prerequisites (Bun 1.3+) and straightforward clone-to-run instructions in CONTRIBUTING.md (`bun install`, `bun dev`), supported by exact version locking via `packageManager` and `bun.lock`. However, it lacks a standard root `.env.example` file despite environment variables being required for LLM provider access, placing it squarely in the Solid band.
Finding Your Way
60Rich contributor context and detailed AGENTS.md files cannot fully replace a top-level architectural map for navigating a massive monorepo.
The repository lacks an architecture document or structured system overview in the root directory, placing it in the 50–69 workable band despite strong auxiliary files like AGENTS.md, CONTEXT.md, and CONTRIBUTING.md. While module boundaries exist via workspaces (`packages/*`), navigating the 6,600+ files without a map or clear top-level directory guide causes friction for newcomers.
Path to Contribute
85Solid contribution guides and templates, though test execution from the root requires navigating package subdirectories.
The repository features a detailed CONTRIBUTING.md, issue templates, PR template, security policy, and code of conduct configuration, clearing the Solid band. However, the root test script explicitly exits with an error ('do not run tests from root'), making test execution documentation slightly fragmented for newcomers.
Signs of Life
85Extensively maintained with robust CI workflows and active governance.
The repository shows strong signs of active maintenance and community life, with extensive CI workflows (26 configurations), a security policy (SECURITY.md), issue templates, code owners, and very recent commit activity (September 2026). It clears the Solid band comfortably due to robust maintenance tracking and tooling, falling just short of Exemplary only because direct metrics on issue/PR response rates are outside the visible file tree.
Open Door
85Legally and socially safe to enter with a clear MIT license and security policy, though a formal Code of Conduct is missing.
Solid Open Door category cleared (85/100): the project provides a clear MIT license, SECURITY.md, CODEOWNERS, issue templates, and comprehensive contributing instructions, though a Code of Conduct file is absent.
First Impression
4 checks passed2 problems found
- lowTopics set
Topics situate the project's domain at a glance and help a newcomer find it.
Fix: Add a few GitHub topics describing the domain and stack.
- lowExamples to learn from
An examples/ directory gives a newcomer something concrete to run and adapt.
Fix: Add an examples/ directory with small, runnable samples.
- README present — The README is the first screen — with none, a newcomer has nothing to land on.
- Repository description set — The one-line description sets expectations before a newcomer even opens the README.
- Status badges — Build/version badges signal at a glance that the project is alive and healthy.
- README shows what it does — A usage/example section lets a newcomer see the tool in action before committing.
Getting Running
6 checks passed1 problem found
- lowOne-click dev container
A .devcontainer lets a newcomer start in a cloud IDE with zero local setup.
Fix: Add a .devcontainer for a one-click, batteries-included environment.
- Lockfile committed — Without a lockfile a newcomer's install resolves differently and hits errors the docs don't mention.
- Prerequisite versions pinned — Unpinned prerequisites are the classic 'works on my machine' first-run failure.
- Env template present — A .env.example shows a newcomer exactly which settings they must fill in to run it.
- One-command environment — A Dockerfile / compose / devcontainer turns a fiddly setup into one command.
- README documents setup — Explicit install steps are the difference between a 5-minute start and giving up.
- Versions pinned exactly — A floating version still drifts — a newcomer can hit a break the maintainer never saw.
Finding Your Way
2 checks passed3 problems found
- mediumArchitecture / overview doc
An overview hands a newcomer the map instead of making them reconstruct it.
Fix: Add an ARCHITECTURE.md (or a 'Project layout' README section) naming the key directories.
- lowNo oversized source file
A single thousand-line file is a wall a newcomer bounces off.
Fix: Split the largest files along their natural seams.
- lowFormatter configured
An auto-formatter means a newcomer never guesses the house style.
Fix: Add a formatter (Prettier, Biome, rustfmt, …) and commit its config.
- Conventional source layout — A familiar src/ · lib/ · app/ layout lets a newcomer guess where things live.
- .editorconfig present — Consistent indentation/encoding keeps the code readable and diffs clean for newcomers.
Path to Contribute
4 checks passed2 problems found
- lowPull-request template
A PR template tells a first-time contributor what a good change includes.
Fix: Add a PULL_REQUEST_TEMPLATE.md.
- lowTask runner
A Makefile / Taskfile gives a contributor a single index of the project's commands.
Fix: Add a Makefile / Taskfile collecting the common dev commands.
- CONTRIBUTING guide — A CONTRIBUTING guide is the difference between a guessed and a guided first PR.
- Issue templates — Issue templates show a newcomer how to file something useful — and that contributions are welcome.
- Test command defined — A documented test command lets a contributor check their change before opening a PR.
- Lint command — A linter lets a first-time contributor catch style issues before review.
Signs of Life
3 checks passed2 problems found
- lowAutomated dependency updates
Dependabot / Renovate activity is a visible heartbeat of ongoing maintenance.
Fix: Enable Dependabot or Renovate.
- lowFunding configured
A FUNDING config signals an invested, sponsored project — not a one-off dump.
Fix: Add a .github/FUNDING.yml if the project accepts sponsorship.
- Tests present — A test suite signals a project that's cared for, not abandoned.
- CI configured — Green CI on every change tells a newcomer the project is actively kept working.
- Changelog — A maintained CHANGELOG shows a newcomer the project ships and records its changes.
Open Door
3 checks passed1 problem found
- lowCode of conduct
A code of conduct states the social ground rules that make it safe to step in.
Fix: Add a CODE_OF_CONDUCT.md (the Contributor Covenant is the de-facto standard).
- License present — With no license the project isn't legally reusable — the door is shut however friendly the README.
- License is a standard one — A non-standard or custom license is a legal question mark a newcomer won't resolve.
- Security policy — A SECURITY.md tells a newcomer how to report a problem responsibly.
Where the grip slips
- mediumVerification Surface+4 pts if fixed
Root test script blocks default execution
Root package.json test script explicitly blocks execution (`echo 'do not run tests from root' && exit 1`), which can cause agents trying to run `npm test` or `bun test` at the root to fail instantly.
Fix: Update root package.json test script to delegate to turbo or document workspace test execution clearly.
- mediumReproducible Setup+3 pts if fixed
Root test script blocks default test invocation
Root test script exits with an error to prevent root execution, forcing agents to discover package-specific test paths.
Fix: Provide a unified turbo or workspace test script at the root level that runs tests across packages correctly.
- mediumCode Navigability+3 pts if fixed
Inconsistent TypeScript strictness across packages
TypeScript strictness and configuration vary across the large monorepo workspace packages.
Fix: Enforce uniform strict tsconfig inheritance across all workspace packages.
- mediumContext Economy+2 pts if fixed
Heavy auxiliary media artifacts clutter file tree and context
Repository contains over 6,600 files, including heavy media artifacts under `artifacts/glm52-rise-video/out/` that consume context and token budgets unnecessarily.
Fix: Move large binary artifacts and demo videos out of the main repository or ensure they are excluded and pruned from git history.
- lowMachine Orientation+2 pts if fixed
Missing architecture doc and llms.txt
No dedicated architecture diagram or top-level llms.txt summary for agent navigation.
Fix: Add an architecture overview or llms.txt to further streamline agent onboarding.
- lowAgent Safety+2 pts if fixed
Missing explicit agent-touch boundaries
The repository lacks a dedicated policy file or machine-readable instruction set defining clear agent-touch boundaries (e.g., explicit read-only or forbidden directories for autonomous agents).
Fix: Add a clear DO NOT TOUCH or read-only boundary block inside AGENTS.md or .opencode/opencode.jsonc to guide autonomous agent actions.
- lowContext Economy+1 pts if fixed
Missing llms.txt guide for agent navigation
Lack of a machine-readable `llms.txt` file or explicit directory-level scoping files across all subpackages hinders efficient agent traversal in a massive monorepo.
Fix: Add an `llms.txt` file at the root to guide agents on package boundaries and key entry points.
Show your score
[](https://latch.fyi/anomalyco/opencode)Share this analysis
https://latch.fyi/anomalyco/opencodeFixed some issues? Re-analyze to measure your progress →
Copy the whole report
Grab the entire verdict in one go — a Markdown block for a README or an issue, plain text, or a prompt you can paste straight into an LLM.