Generating Mod Envs

What it does

When your agent uses it

• Optimize a mod behavior
• Explain envs for /mods learn --env
• Design evaluation scenarios
• Memory fixtures

Example prompts

• “Use the generating-mod-envs skill to generate and reviews mod learning env JSON files for Letta Code local mods”
• “/generating-mod-envs”

Requirements

• Node.js

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Define the behavior and eval before writing JSON.
2. 2Choose a path
3. 3Draft strict JSON. Start from assets/mod-learning-env.template.json if useful. No comments or trailing commas.
4. 4Prefer evaluation.scenarios with at least
5. 5Validate

What it can do on your machine

Read from SKILL.md and the folder at commit 253a3bc. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (TypeScript), which the agent can run.

  Shell commands in SKILL.md call:

  • bun

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Generating Mod Envs loads about 1.5k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 474 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~94

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from letta-ai/letta-code at commit 253a3bc, republished under its Apache-2.0 licence (© letta-ai). 474 words, ~1,533 tokens.

name

generating-mod-envs

description

Generates and reviews mod learning env JSON files for Letta Code local mods. Use when asked to teach, learn, or optimize a mod behavior; create, draft, validate, improve, or explain envs for `/mods learn --env`; or design evaluation scenarios, memory fixtures, requiredResultMarkers, requiredTraceMarkers, negative controls, and candidate diversity hints.

disable-model-invocation

true

user-invocable

true

bun src/skills/builtin/generating-mod-envs/scripts/validate-mod-env.ts path/to/env.json

/mods learn --env=path/to/env.json --model=auto --backend=api --out=/tmp/<slug>-learn

{
  "name": "Hello tool mod learner demo",
  "slug": "hello-tool",
  "objective": "Learn a trusted local mod that registers a read-only hello_mod_ping tool returning a fixed sentinel.",
  "requirements": [
    "Register a tool named hello_mod_ping.",
    "The tool must accept no parameters, require no approval, be parallelSafe, and return the exact string HELLO-MOD-OK."
  ],
  "candidateDiversityHints": [
    "Use the smallest possible tool-only implementation.",
    "Add explicit defensive checks around the tool schema."
  ],
  "modApiHints": [
    "Use export function activate(letta) or a default export.",
    "Use letta.tools.register({ name, description, parameters, requiresApproval, parallelSafe, run }).",
    "A no-argument tool schema is { \"type\": \"object\", \"properties\": {}, \"additionalProperties\": false }."
  ],
  "evaluation": {
    "outputFormat": "stream-json",
    "timeoutMs": 900000,
    "maxTurns": 6,
    "forbiddenTraceMarkers": ["[mods] failed to load", "loaded 0 mod(s)"],
    "scenarios": [
      {
        "name": "happy-path",
        "prompt": "Call the hello_mod_ping tool, then answer with the exact text HELLO-MOD-OK.",
        "requiredResultMarkers": ["HELLO-MOD-OK"],
        "requiredTraceMarkers": ["hello_mod_ping", "\"message_type\":\"tool_return_message\""]
      },
      {
        "name": "negative-control",
        "prompt": "Answer without calling tools: what is 2 + 2?",
        "requiredResultMarkers": ["4"],
        "forbiddenTraceMarkers": ["hello_mod_ping"]
      }
    ]
  }
}

© letta-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts, assets) in src/skills/builtin/generating-mod-envs of letta-ai/letta-code.

• SKILL.md
• assets/mod-learning-env.template.json
• scripts/validate-mod-env.ts

Open the folder on GitHubat commit 253a3bc