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/ilysenko/codex-desktop-linux/validation-playbookgit clone --depth 1 https://github.com/ilysenko/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 | $0.00574 |
| Opus 5 | $0.00000 | $0.00287 |
| Sonnet 5 | $0.00000 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
validation-playbook 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 3d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validation playbook
Fast source checks
bash -n install.sh scripts/lib/*.sh launcher/start.sh.template
bash tests/scripts_smoke.sh
node --test scripts/lib/upstream-linux-package.test.js
node --test scripts/patch-linux-window-ui.test.js scripts/lib/linux-features.test.js linux-features/*/test.js
cargo test -p codex-update-manager
cargo clippy -p codex-update-manager --all-targets -- -D warnings
Source-security matrix
Cover valid, corrupt, unsigned, and wrong-key InRelease; Packages digest
mismatch; package digest mismatch; wrong name/version/architecture; unsupported
architecture; and incomplete official payload. These are unit-tested with local
fixtures and fail closed.
Baseline build
Build with features.example.json, inspect .codex-linux/build-info.json, and
compare the official and staged resources/app.asar hashes. Confirm no runtime
replacement, external CLI, or local content server appears in the staged tree.
Confirm the desktop name is ChatGPT Community, its icon has the community
mark, and the package/bin/path identity is still codex-desktop.
Smoke-test login, project open, terminal, file picker, URI launch, tray, notifications, clean quit, and a second launch on GNOME Wayland, KDE Wayland, and X11. Verify official/custom coexistence and shared-profile single-instance behavior.
When upgrading an installation made by the former Linux port, also exercise the
recognized Browser/Chrome cache migration. Confirm the official clients use
/tmp/codex-browser-use, the Chrome app-server parent is not group-writable,
and unrelated/user-authored plugin caches are unchanged.
Features
Build every retained feature independently and run its adjacent test. Enabled drift must reject a candidate; disabled drift must not be probed. Retired IDs are ignored and arbitrary unknown IDs fail.
Package matrix
Inspect deb, RPM, pacman, AppImage, and Nix outputs on both architectures. Check
official ELF/runtime payload, dependencies, desktop identity, AppArmor path,
updater payload, and absence of official package-manager configuration.
AppImage must never inject --no-sandbox.
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.
- 3d ago First seen · 69 lines · 0 tokens per session scan A aa436a2036aa
validation-playbook is an agent published in the GitHub repository ilysenko/codex-desktop-linux (3,744 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 574 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
ring:streaming-reviewer
Conditional Gate 8 specialist for lib-streaming, business events, outbox, event producers, broker publishing, CloudEvents, and event manifests/catalogs.