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 frankxai/claude-skills-library --skill agent-harness-constructiongit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/frankxai/claude-skills-library/agent-harness-construction)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/agent-harness-construction"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/agent-harness-construction/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/frankxai/claude-skills-library/agent-harness-construction"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/agent-harness-construction.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 | $0.00040 | $0.00371 |
| Opus 5.5 | $0.00016 | $0.00148 |
| Sonnet 5.5 | $0.00008 | $0.00074 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
agent-harness-construction 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 5d 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
Build the harness, keep one chair
An agent is a model plus the harness around it. The harness this estate already runs is the guide, the skills, the MCP servers, starlight-memory, the loops, the evals, the permissions, and the receipts. Add a piece only when one of those is missing.
Lane
- One writer per worktree. Branch
agent/<harness>/<scope>fromorigin/main. - Reviewers stay read-only unless they have their own worktree.
- Do not install Oh My OpenAgent, Ruflo, Oh My ClaudeCode, OpenClaw, Paperclip, Orchestrator.inc, or the ECC
fullprofile as a coordinator.
Tools
- Names stay stable. Inputs stay narrow.
- A result names status, a one-line summary, the next action, and the file or id produced.
- An error names a likely cause, one safe retry, and the condition that means stop.
Context
- The default prompt stays small. Long procedures live in skills that load when asked.
- Point at a file instead of pasting it.
- Compact after the plan is on disk, not in the middle of an edit.
Where this came from
The action-space checklist follows affaan-m/ECC skills/agent-harness-construction at 4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2 (MIT). The one-chair list and the worktree lane are estate law.
Built on SIP.
What ships with it
1 file 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.
- 5d ago First seen · 34 lines · 40 tokens per session scan A 24140b8b1a29
agent-harness-construction is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 371 once invoked, about $0.0002 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 2026-10-11.
Other skills, from other repositories
token-saver
Token optimization guide for Claude Code. This skill should be used when the user wants to reduce API costs, learn model routing strategies, or understand how to use free/cheaper tools (Ollama, Haiku) instead of burning expensive Claude tokens on routine tasks. Triggers on: save tokens, reduce costs, token tips, cheap…
claude-handoff
A handoff tool that prepares a summary of the current conversation for another coding agent and starts that agent in the background.
nav-compact
Clear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when approaching token limits.
python-cli-ops
CLI application patterns for Python. Triggers on: cli, command line, typer, click, argparse, terminal, rich, console, terminal ui.
quick-win-session
Generates guided first-action flows that help users achieve a meaningful result within 60 seconds to boost retention. Use when user wants quick win onboarding, time-to-value optimization, or first success moments.
ship
Commit, push, create PR(s), and auto-finalize — full automation pipeline. Handles uncommitted changes and recently created PRs.