Skip to content

Latest commit

 

History

History
78 lines (53 loc) · 3.91 KB

codex.md

File metadata and controls

78 lines (53 loc) · 3.91 KB

EndoStack in Codex CLI

Codex reads skills from .agents/skills/ and custom agents from TOML files in .codex/agents/. The repository root plugin.json is an Agent Plugins manifest with Codex settings under extensions["com.openai"].

Install

Plugin:

codex plugin marketplace add requie/endostack

Then install EndoStack from the Plugins Directory in the Codex app.

Files, one project:

./install.sh --scope project --agents codex

Files, every project:

./install.sh --scope user --agents codex

Run the installer from a clone of the EndoStack repository. Add --dry-run to see every file it would write, --link to symlink instead of copy, and --uninstall (with the same --scope) to remove exactly what it wrote. On Windows use install.ps1 with the same options.

Where the files land

What Path
Skills .agents/skills/<name>/ or ~/.agents/skills/<name>/
Command-style skills Each also gets agents/openai.yaml with allow_implicit_invocation: false, so Codex runs it only when you type $<name>. With --link this file cannot be added and those skills become model-invocable.
Subagents .codex/agents/<name>.toml or ~/.codex/agents/<name>.toml (fields name, description, developer_instructions). Project agents load only in trusted projects.
Rules A marked block in the project AGENTS.md

The installer records every file it writes, with a hash, in .endostack/install-manifest.json (project) or ~/.endostack/install-manifest.json (user). It never overwrites a file it did not write.

Tool names

EndoStack skills use neutral verbs. In this agent they mean:

EndoStack verb Tool in Codex CLI
Spawn a subagent spawn_agent (unverified)
Ask the user not documented
Track a todo list update_plan (unverified)
Run a shell command shell_command (unverified)
Read a file read_file (unverified)
Edit a file apply_patch
Search the codebase rg and glob_file_search (unverified)
Fetch a URL none; web_search only
Load a skill $<name> or /skills
Transcripts ~/.codex/sessions/<YYYY>/<MM>/<DD>/rollout-*.jsonl (unverified). Files are grouped by date, so filter by the working directory recorded inside each file.

"(unverified)" marks a name or path taken from a third-party source or prior knowledge rather than the vendor's docs. Where a verb has no tool, skills fall back as they describe: plain-text questions, a checklist in the reply, or doing subagent briefs one after another.

Models per subagent

Model choice is per agent definition: the model and model_reasoning_effort fields in an agent TOML file. The spawn call itself takes no model. EndoStack's generated agents set neither field, so they run on the session model. To pin a role, add model to the installed TOML file (the uninstaller then keeps that file because you changed it).

Role assignments live in ~/.endostack/models.toml or the project's .endostack/models.toml, written by setup-endostack.

What degrades here

  • No ask-user tool is confirmed. Skills ask in plain text and stop until you answer.
  • No fetch-by-URL tool. Skills that need a page ask you for it or use curl when the sandbox allows network access.
  • Up to 6 subagents run at once by default ([agents] max_threads), and subagents cannot spawn their own by default (max_depth 1). Larger fan-outs in swarm and security-review run in waves.
  • Multi-model panels (arena, architect, interrogate) run every seat on the session model and vary each seat's brief instead.

Non-interactive mode (used by make-bot-ui for a local bot): codex exec "<prompt>".

Sources