charter

charter is a skill for Claude Code, Codex from otto-haus/otto. It costs 86 tokens per session (2,196 once invoked), scanned A, original, MIT.

An operating contract for long-running work by autonomous software agents. It turns a vague goal into durable files that record the goal, current state, approvals, evidence, and lessons learned.

In plain words
What is it for?
Use it to start, track, resume, and audit multi-step agent work. It supports planning, state tracking, approval gates, activity records, receipts, and completion checks.
Why use it?
It reduces confusion about what the agent is allowed to do, what has already happened, and whether the work is actually finished. It also puts human approval around actions that cannot easily be undone.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/otto-haus/otto/skill
Any agent
npx skills add otto-haus/otto --skill skill
Clone the repo
git clone --depth 1 https://github.com/otto-haus/otto

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for charter

README.md
[![agentmods](https://agentmods.dev/badge/skills/otto-haus/otto/skill.svg)](https://agentmods.dev/skills/otto-haus/otto/skill)
Your own site
<a href="https://agentmods.dev/skills/otto-haus/otto/skill"><img src="https://agentmods.dev/badge/skills/otto-haus/otto/skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,196 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00086 $0.02196
Opus 5 $0.00043 $0.01098
Sonnet 5 $0.00017 $0.00439
Haiku 4.5 $0.00009 $0.00220

Measured 3d ago against content hash a46519864690, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

charter 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 3d ago.

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.

skill/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Charter

Charter turns messy intent into evidence-checked autonomous work.

Object model   Intent -> Charter -> State -> Receipt
Compiler       messy intent -> compact contract (charter.md + charter.yaml)
Runtime        charter.* / state.yaml / ledger.md / approvals / receipts / traces / notes
Loop           Scout -> Judge -> Worker   (+ Auditor proves/rejects done, Recorder keeps files current)
Gates          one-way doors require human approval
Substrate      Files = truth, Memory = lessons, UI = workspace

Core principle

The human owns charter legitimacy.
The agent owns charter operations.

You have better local context (repo state, blockers, prior decisions, tool/runtime constraints, real acceptance criteria, implementation path). So you operationalize vague intent into durable charters. The human decides whether the goal is legitimate and approves one-way doors.

Substrate rules (do not violate)

  • Files = truth. Active charter state lives in files under the runtime root, NOT in Letta memory blocks. Never treat chat or memory as the source of truth for status.
  • Memory = lessons. Write durable lessons learned to memory on completion, not live state.
  • UI = workspace. The command/status output is a view over the files.

Runtime (Files = truth)

Canonical root: $CHARTER_HOME/charters/ (default ~/.charter/charters/, override with CHARTER_HOME). This is intentionally OUTSIDE Letta memory.

charters/
  active.json              { "slug": "<active-slug>" } or { "slug": null }
  <slug>/
    charter.md             human contract (rendered)
    charter.yaml           machine contract — SOURCE OF TRUTH for AC ids, gates, plan ids
    state.yaml             mutable runtime state
    ledger.md              append-only timestamped history
    approvals/             first-class scoped, time-bound approval records (<id>.yaml)
    receipts/              proof artifacts (files, links, logs, screenshots)
    traces/                raw tool/exec traces
    notes/                 detailed companion notes (kept OUT of the contract)

Read the full file on GitHub · 218 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 3d ago First seen · 218 lines · 86 tokens per session scan A a46519864690

Subscribe to this mod's changes

charter is a skill published in the GitHub repository otto-haus/otto (7 stars, last pushed 17d ago), licensed MIT. It adds 86 tokens to every session and 2,196 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

check-work

Check your work with a verification subagent that reviews diffs, runs builds and tests, and evaluates correctness. Read this file for instructions. Use when asked to "check work", "verify changes", "self-verify", "/check-work", "/check", "/verify", or "/self-verify".

RoyZhao1991/LingShu · 64 tokens

create-skill

Interactively create a new Grok skill (SKILL.md + optional scripts/references). Use when the user wants to create a skill, scaffold a skill, or runs /create-skill.

RoyZhao1991/LingShu · 43 tokens

imagine

How to use the imagegen and imageedit tool calls in Grok Build: when to build a visual with code instead of generating it, prompt-craft, reference-first handling of real people, factual grounding, and asset-consistency. Load this whenever generating or editing an image is on the table, i.e. when an imagegen or…

RoyZhao1991/LingShu · 97 tokens

best-of-n

Implement a task N ways in parallel and pick the best. Spawns multiple subagents in isolated worktrees, evaluates all candidates, and applies the winner. Use when asked to "best of n", "try multiple approaches", "parallel implementations", "/best-of-n", or "/bon".

RoyZhao1991/LingShu · 62 tokens

help

Grok documentation and configuration help. Use when users ask about setup, configuration, MCP servers, authentication, skills, slash commands, keyboard shortcuts, or any Grok feature. Also use proactively when you detect a user is having trouble with setup or onboarding.

RoyZhao1991/LingShu · 53 tokens

safety-guardrails

Flags risky shell commands and unsafe tree ops.

andreaswasita/copilot-agents-dojo · 15 tokens