saving-token
v1.3.0
Published
A native writer makes file changes; the host directs and reviews. The writer model is selected during setup, while the host model and global defaults stay unchanged.
Readme
saving-token
A native writer makes file changes; the host directs and reviews. The writer model is selected during setup, while the host model and global defaults stay unchanged.
Inspired by karpathy-guidelines.
The writer is used only when the host model is stronger; otherwise the host works directly.
Install
Interactive setup
bash skills/saving-token/scripts/setup.shUse Up/Down and Enter to choose the platform, writer model, optional reasoning effort, and final action. Press Esc to cancel. The final menu starts on Cancel. Model entries are suggestions only; availability is not checked. The effort menu includes the host default and values accepted by the target; account and model support still depend on the host.
The model menu has no free-text entry. Use --model for a custom model ID or
for non-interactive setup:
bash skills/saving-token/scripts/setup.sh \
--target codex --model '<model-id>' --yes--target and --model are required without a terminal. Add
--reasoning-effort <effort> when supported by the selected model. --yes
approves the displayed installation and replacements; it never chooses a
model. Rerun setup to change the writer. Extra files in an existing Skill
directory are preserved.
npm wrapper
After publication, run:
npx saving-token@latest install --agent codexThe wrapper supports install --agent codex and update-models --agent codex.
Use the Bash script directly for --target, --model, --reasoning-effort,
or --yes.
To choose a new writer model and reasoning effort in an existing Codex installation, run:
npx saving-token@latest update-models --agent codexUse Up/Down and Enter to choose the model, then the reasoning effort.
It updates the model list and only the writer configuration; it shows no
platform or confirmation menus. Use the Bash script with
--update-models --target claude or cursor for those platforms.
Installed paths
| Platform | Skill | Writer configuration |
|---|---|---|
| Codex | ${CODEX_HOME:-~/.codex}/skills/saving-token/ | ${CODEX_HOME:-~/.codex}/agents/saving-token-writer.toml |
| Claude Code | ~/.claude/skills/saving-token/ | ~/.claude/agents/saving-token-writer.md |
| Cursor | ~/.cursor/skills/saving-token/ | ~/.cursor/agents/saving-token-writer.md |
Restart the host, then invoke $saving-token in Codex or /saving-token in
standalone Claude Code and Cursor. A generated configuration does not prove
runtime routing; verify the model in exposed task metadata when available.
Claude Code and Cursor may substitute a model under account or administrator
policy.
The writer implements and verifies delegated changes. The host personally reviews the actual changes and verification evidence against the requirements, sends defects back to the same writer for fixes and re-review, and announces completion only after review passes.
Claude Code plugin
/plugin marketplace add JerryWu1234/saving-token
/plugin install saving-token@saving-tokenThe plugin collects writer_model through its configuration and leaves effort
to the host. Invoke /saving-token:saving-token; its writer is
saving-token:saving-token-writer. Use either the plugin or standalone setup.
Official references: Codex subagents, Claude subagents, Claude plugins, Cursor subagents, and Agent Skills.
