Octos is a self-hosted AI assistant that runs on a user's computer and can connect to different AI providers, execute code, browse the web, remember information, schedule jobs, and create documents through browser, terminal, and messaging interfaces. The catalogue entries extend or configure this assistant's workflows.
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 skills add octos-org/octos --skill harness-starter-codinggit clone --depth 1 https://github.com/octos-org/octosWrote 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/octos-org/octos/harness-starter-coding)<a href="https://agentmods.dev/skills/octos-org/octos/harness-starter-coding"><img src="https://agentmods.dev/badge/skills/octos-org/octos/harness-starter-coding/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/octos-org/octos/harness-starter-coding"><img src="https://agentmods.dev/badge/skills/octos-org/octos/harness-starter-coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00029 | $0.00466 |
| Opus 5.5 | $0.00012 | $0.00186 |
| Sonnet 5.5 | $0.00006 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
harness-starter-coding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Harness Starter: Coding
A coding-assistant starter. Produces a unified-diff file as its primary deliverable plus a preview artifact listing the changed files. Copy this crate when you want to build an app that ships a patch/diff/changeset.
What this starter demonstrates
primary = "patches/*.diff"— the canonical deliverable.preview = "patches/*.files.txt"— a secondary artifact the operator surface may use to summarize the change.file_size_min:$primary:64— validator rejects empty patches.- Multi-artifact spawn task binding (
artifacts = ["primary", "preview"]) so the runtime delivers both files.
See docs/OCTOS_HARNESS_DEVELOPER_GUIDE.md for the full contract.
Tools
propose_patch
Render a patch as a unified-diff file plus a preview file list.
{
"title": "Fix typo in hello",
"hunks": [
{
"file": "src/lib.rs",
"new_content": "pub fn hello() -> &'static str {\n \"hi\"\n}\n"
}
]
}
Parameters:
title(required): short title; derives the filename (patches/fix-typo-in-hello.diff).hunks(required, non-empty): list of{file, new_content}hunks. Each hunk becomes a full-file replacement hunk in the diff.
Artifacts:
patches/<slug>.diff— primary unified-diff file.patches/<slug>.files.txt— preview list of changed files.
Replace this stub
The starter generates full-file replacement hunks. A real coding assistant
should use similar or diff to compute minimized unified diffs, and
consider running the patch through git apply --check in a validator
before delivery.
What ships with it
6 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.
- 2mo ago First seen · 60 lines · 29 tokens per session scan A 7c2bb64c7fd3
harness-starter-coding is a skill published in the GitHub repository octos-org/octos (766 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 466 once invoked, about $0.0001 per session on Opus 5.5. 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.
harness-starter-coding compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| harness-starter-codingoctos-org/octos | Skill | 766 | today | Apache-2.0 | A | 29 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |