Shellm Architecture Reference

What it does

When your agent uses it

• Understanding how shellm's identity, memory and trajectory pieces fit together
• Debugging unexpected agent behavior inside the shellm system
• Looking up which bin/ script handles a specific shellm capability

Example prompts

• “Explain how shellm's identity activation sets up environment variables.”
• “Which script handles the recursive execute-in-shell loop in shellm?”
• “Debug why this shellm agent's memory search isn't returning results.”

Requirements

• bash

Workflow steps

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

1. 1think step loads the think prompt template from $IDENTITY_DIR/prompts/think.md
2. 2Replaces {{identity_name}} and {{goals}} in the template
3. 3Appends recent traj context (last N steps via traj tail)
4. 4Calls shellm with this prompt — shellm executes bash, loops until FINAL
5. 5Writes the resulting thought or action to traj
6. 6If it was an action, forks a child branch, executes via shellm, merges back
7. 7Dispatches thought processes (TPs) — each TP gets recent thoughts and can write to traj/mem

What it can do on your machine

Read from SKILL.md and the folder at commit d77aadd. 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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

  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 these keys or tokens, usually read from environment variables:

  • ANTHROPIC_API_KEY
  • OPENAI_API_KEY

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

Context cost

Shellm Architecture Reference loads about 2k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 771 words of instructions outside code blocks.

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

~59

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

~2k

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

• NoteMentions a .env fileSKILL.md:122

  .env                  (optional) identity-specific env vars

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from laude-institute/headlong at commit d77aadd, republished under its Apache-2.0 licence (© laude-institute). 771 words, ~1,989 tokens.

name

shellm

description

Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.

llm              raw LLM calls (Anthropic, OpenAI, Gemini)
shellm           recursive execute-in-shell loop on top of llm
traj / context   step log (DAG) + message assembly for multi-turn
mem / skills     persistent memory + learnable capabilities
identity         isolated agent identities (own mem, skills, traj)
think / chat     autonomous thinking + human conversation
focus            goal tracking

source .identities/myagent/activate   # activate in current shell
deactivate_identity                    # undo
identity shell myagent                 # or: start a subshell

.identities/<name>/
  info.txt              name=, cwd=, created=, think_model=, interval=
  activate              source-able activation script
  core_identity_prompt.md  (optional) custom system prompt
  .env                  (optional) identity-specific env vars
  memories/             mem entries (markdown files)
  skills/               installed skills
    .skillsrc           skill remotes config
  kernel/               kernel skills (always loaded)
    mem/SKILL.md        bootstrapped mem skill
  .trajectories/        trajectory files
    trajectory.jsonl          main consciousness stream
    blobs/              spilled large fields
  .shellm/              shellm working state
  workdir/              working directory for think cycles

© laude-institute, 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

Just SKILL.md in skills/shellm of laude-institute/headlong.

Open the folder on GitHubat commit d77aadd