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 commands/dojocodinglabs/code-sensei/importgit clone --depth 1 https://github.com/DojoCodingLabs/code-senseiWhat 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 | $0.00016 | $0.00826 |
| Opus 5 | $0.00008 | $0.00413 |
| Sonnet 5 | $0.00003 | $0.00165 |
| Haiku 4.5 | $0.00002 | $0.00083 |
Grade A, and why
import 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 yesterday.
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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Import
You are CodeSensei 🥋 by Dojo Coding. The user wants to import a profile from an export file.
Instructions
The user must provide the path to the export file as an argument.
Example: /code-sensei:import ~/code-sensei-export-2026-03-03.json
If no argument is provided, show:
🥋 CodeSensei — Import Profile
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Usage: /code-sensei:import [path to export file]
Example:
/code-sensei:import ~/code-sensei-export-2026-03-03.json
To create an export file first, run:
/code-sensei:export
Step 1: Validate and preview using the import script
Run:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/import-profile.sh [path provided by user]
Interpret the JSON response:
missing_arg→ show the usage block abovejq_missing→ tell the user jq is required and how to install itfile_not_found→ tell the user the file was not foundinvalid→ tell the user the export file is not a valid CodeSensei exportpreview→ continue to Step 2
Step 2: Show the import preview
For status = preview, show:
🥋 CodeSensei — Import Preview
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Import file: [path]
Exported at: [exported_at]
Schema version: [schema_version]
Plugin version: [plugin_version]
Profile to import:
[Belt Emoji] Belt: [target_summary.belt]
⚡ XP: [target_summary.xp]
🧠 Concepts mastered: [target_summary.concepts_mastered]
📊 Quizzes taken: [target_summary.quizzes_total]
🔥 Streak: [target_summary.streak_current] days
Current profile:
[If current_summary is null: "No existing profile found"]
[Else show the same five lines for current_summary]
⚠️ WARNING: This will overwrite your current profile.
A backup will be saved to [backup_path]
Type "yes" to confirm the import, or anything else to cancel.
Step 3: Wait for confirmation
If the user does not clearly confirm, show:
↩️ Import cancelled. Your current profile was not changed.
Step 4: Apply the import
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.
- yesterday First seen · 120 lines · 16 tokens per session scan A 14aa4c57cfc1
import is a command published in the GitHub repository DojoCodingLabs/code-sensei (14 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 826 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
decide
Forces structured decision-making and creates an auditable Agent Decision Record (AgDR).
agent-preflight
Run a local repo preflight before Claude Code gets tool access.
agent-manager-skill
Use /agent-manager-skill to orchestrate multiple local CLI agents via tmux using agent-manager-skill (start/stop/monitor/assign + cron-friendly scheduling).
better-auth:add-plugin
Add a better-auth plugin to an existing project. Configures server and client plugins with proper imports.
better-auth:setup
Interactive setup wizard for better-auth authentication. Guides through database, framework, OAuth providers, and plugin configuration.
providers
Display Better Auth available authentication providers and their configuration.