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 skills/otto-haus/otto/skillnpx skills add otto-haus/otto --skill skillgit clone --depth 1 https://github.com/otto-haus/ottoWrote 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.
[](https://agentmods.dev/skills/otto-haus/otto/skill)<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>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.
| Model | Per session | Once 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 |
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.
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)
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.
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.
- 3d ago First seen · 218 lines · 86 tokens per session scan A a46519864690
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.
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".
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.
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…
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".
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.
safety-guardrails
Flags risky shell commands and unsafe tree ops.