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 charlie947/agent-harness-starter --skill skillgit clone --depth 1 https://github.com/charlie947/agent-harness-starterWrote 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/charlie947/agent-harness-starter/skill)<a href="https://agentmods.dev/skills/charlie947/agent-harness-starter/skill"><img src="https://agentmods.dev/badge/skills/charlie947/agent-harness-starter/skill/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/charlie947/agent-harness-starter/skill"><img src="https://agentmods.dev/badge/skills/charlie947/agent-harness-starter/skill.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00112 | $0.01589 |
| Opus 5 | $0.00056 | $0.00794 |
| Sonnet 5 | $0.00022 | $0.00318 |
| Haiku 4.5 | $0.00011 | $0.00159 |
Grade A, and why
agent-harness-setup 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 10d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Harness Setup
This skill walks the user through installing the six-component agent harness from the MarTech AI newsletter. It is the interactive companion to the agent-harness-starter repo.
The user runs the skill, you ask the setup questions, you write the files. Charlie's directive: ask in plain prose, not the AskUserQuestion picker (feedback_no_question_picker).
Step 1 — Ask which path
Open with:
Welcome to the agent harness setup. Two paths:
- Global harness — your personal
~/.claude/directory (Personalisation, Memory, Skills, Agents). Recommended first time.- Project harness — a
CLAUDE.mdfor a specific project you're already inside.Which would you like?
If global → Step 2. If project → Step 7.
Step 2 — Global setup, pre-flight
Run bash skill/scripts/setup.sh (relative to wherever the repo was cloned). This creates:
~/.claude/CLAUDE.md (empty, populated next)
~/.claude/memory/MEMORY.md (index template)
~/.claude/skills/ (empty)
~/.claude/agents/ (empty)
If ~/.claude/CLAUDE.md already exists, ask the user before overwriting. Default: rename existing to CLAUDE.md.backup-{timestamp} and continue.
Step 3 — Personalisation interview
Ask the user, one block at a time, in plain prose:
- Your role and what you do. "Who are you and what do you spend your time on? One paragraph."
- Your voice. "How do you write? British or US English? Long sentences or short? Any punctuation you ban (em dashes, semicolons)? Any words you ban (leverage, tapestry, deep dive)?"
- Your output defaults. "What format do you want answers in by default? Markdown? Plain text? Save to file?"
- Your workflow rules. "When should I plan before executing? When should I ask vs. just go? How do I handle corrections?"
- The audience for your work. "Who reads what you ship? Marketers? Engineers? Founders?"
After all five, draft the global CLAUDE.md based on the template at templates/CLAUDE.md with the user's answers filled in. Show it to them, ask for edits, then save to ~/.claude/CLAUDE.md.
What ships with it
2 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.
- 10d ago First seen · 143 lines · 112 tokens per session scan A e77215a5dc57
agent-harness-setup is a skill published in the GitHub repository charlie947/agent-harness-starter (22 stars, last pushed 3mo ago), licensed MIT. It adds 112 tokens to every session and 1,589 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
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.