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 instructions/josephbartlett/windows-appshot-codex/agents-mdgit clone --depth 1 https://github.com/josephbartlett/windows-appshot-codexWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/josephbartlett/windows-appshot-codex/agents-md)<a href="https://agentmods.dev/instructions/josephbartlett/windows-appshot-codex/agents-md"><img src="https://agentmods.dev/badge/instructions/josephbartlett/windows-appshot-codex/agents-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00822 | $0.00822 |
| Opus 5 | $0.00411 | $0.00411 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
windows-appshot-codex AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This repository packages the windows-appshot Codex plugin.
Project Shape
.codex-plugin/plugin.jsonis the release manifest. Keep itsversionfield semantic.README.mdis user-facing plugin documentation. Keep$windows-appshotcommands before direct PowerShell script references unless the section is explicitly for development, validation, or advanced script usage.skills/windows-appshot/SKILL.mdis the Codex skill entrypoint.scripts/New-Appshot.ps1captures the foreground Windows window into a local appshot bundle.scripts/Start-AppshotHotkey.ps1starts the optional hotkey listener.scripts/Install-WindowsAppshotPlugin.ps1installs or updates the plugin checkout and personal marketplace entry.scripts/Test-WindowsAppshotPlugin.ps1is the repo-local validation entrypoint used by CI.
Safety Rules
- Do not edit Codex session files or private Codex storage.
- Do not commit generated
appshots/output or logs. - Do not commit or push without explicit user approval in the current conversation.
- Keep the default command target as
NewThreadunless there is a deliberate release decision to change it. - Preserve PowerShell single-quote escaping in generated clipboard commands.
- Keep the install/update script idempotent and non-destructive. It may clone, fast-forward pull, update the marketplace entry, and run
codex plugin add; it must not delete unrelated user files. - Preserve bounded UI Automation traversal and generic Pane/editable/password/off-screen filtering.
- Do not reintroduce aggregate UI Automation
TextPatternextraction without a privacy review. - Do not make query-based capture silently accept ambiguous matches. Browser tab activation must remain confirmation-first unless
-NoWindowConfirmationis explicitly supplied for tests or trusted automation. -TargetIndexis allowed as explicit selection for regular windows after listing. If the indexed target is a browser tab, it must still require-NoWindowConfirmation.- Query capture must verify that the selected window is foreground before screenshot capture. Browser-tab capture must also verify UI Automation selected-tab state when available or a strong active-title match for the selected tab.
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.
- 4d ago First seen · 54 lines · 822 tokens per session scan A cc8a0a2ec96f
windows-appshot-codex AGENTS.md is an instructions file published in the GitHub repository josephbartlett/windows-appshot-codex (1 stars, last pushed 3mo ago), licensed MIT. It adds 822 tokens to every session, about $0.0041 per session on Opus 5. 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 2026-08-31.
Other instructions, from other repositories
codexia AGENTS.md
AGENTS.md instructions for milisp/codexia, covering agents.md, project info, project tech, common commands and project structure.
CodexPotter AGENTS.md
AGENTS.md instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.
codex-docs AGENTS.md
AGENTS.md instructions for chenrui333/codex-docs, covering agents notes, scope, generated content boundaries, local workflow and validation expectations.
vibe-codex AGENTS.md
Instructions for kks0488/vibe-codex, covering vibe-codex (codex cli), repo conventions, openai docs and handy commands.
codex-status-bar AGENTS.md
Instructions for yuriipalam/codex-status-bar, covering repository instructions, engineering expectations, verification and release procedure.
odin-codex-plugin AGENTS.md
AGENTS.md instructions for OutlineDriven/odin-codex-plugin, covering codex coding agent adherences, token-efficient cli output, tool hierarchy, core system & file ops and search & discovery.