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 agentmods add agents/distsystem/codex-desktop-linux/repository-mapgit clone --depth 1 https://github.com/distsystem/codex-desktop-linuxWhat 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 | $0.00000 | $0.03451 |
| Opus 5 | $0.00000 | $0.01725 |
| Sonnet 5 | $0.00000 | $0.00690 |
| Haiku 4.5 | $0.00000 | $0.00345 |
Grade A, and why
repository-map 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 2d 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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Repository Map
This map keeps the detailed file ownership notes out of AGENTS.md while
preserving the source-of-truth routing agents need before editing.
Repo Orchestration
install.shTop-level installer entrypoint. It sourcesscripts/lib/*.sh, keeps the high-level build sequence small, and emitscodex-app/start.shfrom the launcher template plus an install-time identity prelude.MakefileConvenience targets for setup, fresh/build/install/package flows, native package autodetection, dev side-by-side app identities, AppImage, cleanup, and bootstrap workflows. Important targets includesetup-native,bootstrap-native,install-native,update-native,appimage,package, andinstall, plus granular helpers (build-app,build-app-fresh,rebuild,rebuild-install,rebuild-next,build-dev-app,run-app,run-dev-app,inspect-upstream,build-updater,service-enable,service-status,check,test,clean-dist,clean-state).scripts/bootstrap-wizard.shGuided native setup/update helper. It can discover Linux features, edit feature config, validate feature relationships, install native packages, and perform explicit feature-owned cleanup.Cargo.tomlWorkspace root forcomputer-use-linux,read-aloud-linux,record-replay-linux, andupdater.flake.nix/flake.lockNix flake that pins upstream DMG, Cargo dependency, and Node dependency hashes. Usescripts/ci/update-nix-hashes.shto refresh pins.nix/Nix integration modules:home-manager-module.nix,nixos-module.nix, andnative-modules/rebuild support for the flake..devcontainer/devcontainer.json/.devcontainer/DockerfileGeneric build/test container with Rust, Node 22/npm, packaging tools,rustfmt, andclippy.
Launcher
launcher/start.sh.templateRuntime launcher body. Edit this for webview server lifecycle, warm-start handoff, CLI preflight, GUI prompts, URL-scheme handling, runtime Linux feature hooks, bundled plugin cache sync, and process/liveness behavior. Single-instance enforcement uses anflocklauncher lock plus serialized bootstrap around detection/spawn/app.pid, and a/procrunning-app scan filtered byCODEX_LINUX_INSTANCE_ID.launcher/webview-server.pyStandalone Python HTTP server for local webview assets, serving explicit no-store/no-cache headers. It is started and supervised by the launcher.packaging/linux/codex-packaged-runtime.shNative-package-only runtime helper loaded optionally by the launcher.packaging/appimage/codex-appimage-runtime.shAppImage-only runtime helper.
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.
- 2d ago First seen · 308 lines · 0 tokens per session scan A cac9bc3ee9f3
repository-map is an agent published in the GitHub repository distsystem/codex-desktop-linux (11 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,451 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.