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 instructions/bestagentkits/cloud-harness-mcp/agents-mdgit clone --depth 1 https://github.com/bestagentkits/cloud-harness-mcpWrote 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/instructions/bestagentkits/cloud-harness-mcp/agents-md)<a href="https://agentmods.dev/instructions/bestagentkits/cloud-harness-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bestagentkits/cloud-harness-mcp/agents-md.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 5.1 | $0.01708 | $0.01708 |
| Opus 5 | $0.00854 | $0.00854 |
| Sonnet 5 | $0.00342 | $0.00342 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
cloud-harness-mcp AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Harness MCP collaborator guide
Purpose and authority
Cloud Harness MCP is intentionally a private, single-owner remote coding harness. Preserve that threat model: it permits arbitrary repository-controlled execution inside a constrained executor, but it is not a hostile multi-tenant sandbox.
Start with README.md. Read the relevant document under docs/
before changing its boundary. Code, schemas, tests, manifests, and scripts own
WHAT and HOW; documentation owns WHY and WHERE. Point docs to executable owners
instead of copying behavior, defaults, command inventories, or configuration.
Navigation
| Concern | Read first | Executable authority and evidence |
|---|---|---|
| Trust model and isolation | docs/security-model.md |
apps/api/src/request-security.ts, apps/runner/src/workspace-service.ts, test/integration/docker-sandbox.docker.test.ts |
| Public MCP contract | docs/mcp-api.md |
packages/contracts/src/, apps/api/src/mcp-server.ts, packages/contracts/test/, test/integration/ |
| API/runner boundary | docs/system-architecture.md |
apps/api/src/, apps/runner/src/, compose*.yaml, scripts/verify-compose-boundaries.mjs |
| Repository and executor behavior | docs/security-model.md |
apps/runner/src/repository-policy.ts, worker/, runner and Docker tests |
| Configuration | docs/configuration.md |
.env.example, packages/contracts/src/config.ts, apps/api/src/config.ts, apps/runner/src/config.ts, compose*.yaml |
| Development and verification | docs/development.md |
package.json, .github/workflows/ci.yml, tests |
| Deployment and recovery | docs/deployment.md, docs/operations.md, docs/troubleshooting.md |
deploy/, compose.production.yaml, scripts/verify-production.mjs, scripts/deploy-canary.mjs |
| Operator dashboard UI | docs/design-guidelines.md |
apps/api/dashboard/, apps/api/src/dashboard-router.ts, apps/api/src/dashboard-assets.ts, apps/api/test/dashboard-ui-contract.test.ts |
| Official user docs & guides | docs-site/ |
docs-site/, scripts/build-docs-reference.mjs, npm run docs:build |
| Agent skill & MCP tool guidance | .agents/skills/cloudharness/SKILL.md |
.agents/skills/cloudharness/, plugins/cloud-harness/, packages/contracts/test/cloudharness-skill-contract.test.ts, npm run plugin:sync |
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 · 112 lines · 1,708 tokens per session scan A dc75e486a9bd
cloud-harness-mcp AGENTS.md is an instructions file published in the GitHub repository bestagentkits/cloud-harness-mcp (8 stars, last pushed 4d ago), licensed MIT. It adds 1,708 tokens to every session, about $0.0085 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 instructions, from other repositories
eve AGENTS.md
AGENTS.md instructions for vercel/eve, covering agents.md, about eve, repository layout, git workflow and commands.
learn-harness-engineering CLAUDE.md
Instructions for walkinglabs/learn-harness-engineering, covering claude.md, project overview, commands, documentation site and run lecture code examples.
trueforge AGENTS.md
AGENTS.md instructions for truefoundry/trueforge, a project described as: The open-source agent harness - the runtime layer that turns an LLM into a working agent.
aif-handoff CLAUDE.md
Instructions for lee-to/aif-handoff, covering claude.md, project overview, tech stack, project structure and key entry points.
har AGENTS.md
AGENTS.md instructions for os-factory/har, covering har — agent development guide, har / agent environment, harnesses in this repo, harness workflow (dogfooding) and run history.
sprawling AGENTS.md
Instructions for 2youg1/sprawling, covering agents.md — how work is done in this repository, the loop, read before you write, one change, five steps and the rules a machine holds.