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 humaisali/Awesome-AI-Skills --skill agent-harnessgit clone --depth 1 https://github.com/humaisali/Awesome-AI-SkillsWrote 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/humaisali/awesome-ai-skills/agent-harness)<a href="https://agentmods.dev/skills/humaisali/awesome-ai-skills/agent-harness"><img src="https://agentmods.dev/badge/skills/humaisali/awesome-ai-skills/agent-harness/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/humaisali/awesome-ai-skills/agent-harness"><img src="https://agentmods.dev/badge/skills/humaisali/awesome-ai-skills/agent-harness.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 | $0.00170 | $0.01909 |
| Opus 5 | $0.00085 | $0.00955 |
| Sonnet 5 | $0.00034 | $0.00382 |
| Haiku 4.5 | $0.00017 | $0.00191 |
Grade A, and why
agent-harness 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 11d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Harness
You are a harness operator, not a hero. The loop — not your optimism — decides when work is done. Your job: compile the goal into tasks with checks, execute one task at a time, let the controller adjudicate verification, and stop when the state machine says stop.
The contract
GOAL → goal_compiler → PLAN → loop_controller: [execute → verify]* → CLOSE
↑______retry (≤ max_attempts, changed approach)
└── ESCALATE on exhausted budgets — never fake success
Three layers, all JSON: a committed per-domain manifest (what skills/tools/checks exist), a per-goal plan (which tasks, which verifications, what "done" means), and a per-run state file (the single source of truth; a fresh session resumes from it alone).
Quick start
# 0. Pick the domain manifest (18 committed under assets/harnesses/, e.g. engineering-team.json)
ls assets/harnesses/
# 1. Compile the goal (refuses vague goals with exit 3 + forcing questions)
python3 scripts/goal_compiler.py \
--goal "audit the payments service and design an SLO with an error budget" \
--manifest assets/harnesses/engineering.json --out plan.json
# 2. Initialize the loop state
python3 scripts/loop_controller.py init --plan plan.json --state .agent-harness/state.json
# 3. Drive the loop — repeat until directive is "close" or "escalate"
python3 scripts/loop_controller.py next --state .agent-harness/state.json
# → {"action": "execute", "task": "T1", ...}: open the task's skill (SKILL.md at
# skill_path), do the work with its tools, then:
python3 scripts/loop_controller.py record --state .agent-harness/state.json \
--task T1 --phase execute --exit-code 0
# → the controller runs the task's checks ITSELF (subprocess, timeout, evidence log):
python3 scripts/loop_controller.py verify --state .agent-harness/state.json --task T1 --cwd <repo-root>
# 4. Close — refused (exit 4) while any task is unverified and unwaived
python3 scripts/loop_controller.py close --state .agent-harness/state.json
What ships with it
25 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.
- assets/harness_manifest.schema.json 3.1 KB
- assets/harnesses/business-growth.json 9.1 KB
- assets/harnesses/business-operations.json 19 KB
- assets/harnesses/c-level-advisor.json 82 KB
- assets/harnesses/commercial.json 21 KB
- assets/harnesses/compliance-os.json 7.8 KB
- assets/harnesses/engineering-team.json 78 KB
- assets/harnesses/engineering.json 129 KB
- assets/harnesses/finance.json 6.1 KB
- assets/harnesses/loop-library.json 1.3 KB
- assets/harnesses/markdown-html.json 14 KB
- assets/harnesses/marketing-skill.json 68 KB
- assets/harnesses/marketing.json 3.1 KB
- assets/harnesses/product-team.json 25 KB
- assets/harnesses/productivity.json 32 KB
- assets/harnesses/project-management.json 16 KB
- assets/harnesses/ra-qm-team.json 35 KB
- assets/harnesses/research-ops.json 19 KB
- assets/harnesses/research.json 22 KB
- references/agentic_loop_canon.md 6.1 KB
- references/domain_harness_design.md 6.5 KB
- references/verification_discipline.md 6.2 KB
- scripts/goal_compiler.py 8.1 KB runs code
- scripts/harness_manifest_builder.py 9.2 KB runs code
- scripts/loop_controller.py 16 KB runs code
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.
- 11d ago First seen · 131 lines · 170 tokens per session scan A cc31a8a95072
agent-harness is a skill published in the GitHub repository humaisali/Awesome-AI-Skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 170 tokens to every session and 1,909 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…