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 skills/treylom/thiscodex/create-botnpx skills add treylom/ThisCodex --skill create-botgit clone --depth 1 https://github.com/treylom/ThisCodexWhat 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 | $0.00069 | $0.03939 |
| Opus 5 | $0.00034 | $0.01969 |
| Sonnet 5 | $0.00014 | $0.00788 |
| Haiku 4.5 | $0.00007 | $0.00394 |
Grade C, and why
create-bot scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 "$STATE_DIR/.env" 2>/dev/null || true Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Equivalent `~/.codex/config.toml` registration: How it starts
The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a Discord bot with ThisCodex
Carry the Discord Developer Portal flow to completion. The default is browser automation, with exactly three human-only security gates. Do not replace this flow with a list of portal instructions when an interactive browser MCP is available.
This is a Codex-surface port of the companion ThisCode
skills/create-bot/SKILL.md. Keep its portal order, intent set, permissions,
and security boundaries. This skill owns the Discord application and token
stage; use thiscodex init for the surrounding local bot workspace setup.
Inputs
Confirm these before a live run:
- bot/application name;
- the ThisCodex Discord state directory that will receive
.env; - DM-only or a named server/private-channel exposure;
- whether the user requested
dry-runor a live portal run.
If the state directory is not yet confirmed, stop and run guided
thiscodex init. Do not invent a path.
0. Dry-run boundary
In dry-run mode, verify this document, discover browser capabilities, and explain the three human gates. A dry-run must not navigate to Discord, mutate Codex configuration, create an application, reset a token, or invite a bot.
Package tests and unattended CI are always dry-run. A real browser E2E uses a real account and therefore requires the account owner to be present.
0.5 Automation mode and the code gate
thiscodex init asks Automatic (auto / 자동) or Manual (manual / 수동)
as its first interaction. Do not ask the same question again here. Before any
manual handoff, call the shipped code gate; prose judgment is not evidence:
thiscodex automation-gate --gate <stable-gate-name> \
--status <succeeded|failed|human_required> \
--surface <policy-surface> --flow <policy-flow> \
--provider <observed-provider-or-empty> --operation <policy-operation> \
--terminal <policy-terminal> --reason-code <policy-reason-code>
In auto mode an unlisted gate is blocked. For attempt-required gates the CLI
accepts only a completion envelope independently written by the app-server
bridge for the current turn; flags or prose cannot claim an attempt. Immediately
before the relevant tool call, bind its policy gate and operation with
thiscodex automation-attempt --gate <stable-gate-name>. Evidence without that
pre-attempt coordinate cannot satisfy another operation in the same flow. The first
provider observed for a flow is bound to that flow. The gate writes only
policy labels plus evidence coordinates (never arguments, page text, URL,
result, or raw error) to
~/.config/thiscodex/automation-attempts.jsonl.
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 · 401 lines · 69 tokens per session scan C bde1f40116ee
create-bot is a skill published in the GitHub repository treylom/ThisCodex (17 stars, last pushed 17d ago), licensed MIT. It adds 69 tokens to every session and 3,939 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.