Project settings that connect a debugging service, restrict access to credential files, and define safety hooks around tool use, stopping, and notifications.

Debugging through the configured service and controlling which sensitive files and settings the agent may read or change.

They reduce the chance of exposing secrets such as cloud credentials, private keys, or environment files while the agent works.

openharness — Settings file by mifunedev

Install

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.

agentmods

npx agentmods add settings/mifunedev/openharness/settings

Clone the repo

git clone --depth 1 https://github.com/mifunedev/openharness

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan C 2 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade C, and why

openharness scanned grade C with 2 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 2d 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

"Read(file_path=**/.aws/credentials)",

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

"Read(file_path=**/.wget-hsts)",

.claude/settings.json · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "enabledMcpjsonServers": ["debugmcp"],
  "permissions": {
    "deny": [
      "Read(file_path=**/.env*)",
      "Read(file_path=**/*.pem)",
      "Read(file_path=**/*.key)",
      "Read(file_path=**/*.cert)",
      "Read(file_path=**/*.p12)",
      "Read(file_path=**/*id_rsa*)",
      "Read(file_path=**/*id_ed25519*)",
      "Read(file_path=**/.aws/credentials)",
      "Read(file_path=**/.aws/config)",
      "Read(file_path=**/.gcp/**)",
      "Read(file_path=**/settings.local.json)",
      "Write(file_path=**/settings.local.json)",
      "Edit(file_path=**/settings.local.json)",
      "NotebookEdit(notebook_path=**/settings.local.json)",
      "Read(file_path=**/.config)",
      "Read(file_path=**/.config/**)",
      "Write(file_path=**/.config)",
      "Write(file_path=**/.config/**)",
      "Edit(file_path=**/.config)",
      "Edit(file_path=**/.config/**)",
      "NotebookEdit(notebook_path=**/.config/**)",
      "Bash(command=*/.config/*)",
      "Bash(command=*/.config)",
      "Read(file_path=**/.config/gcloud/**)",
      "Read(file_path=**/.azure/**)",
      "Read(file_path=**/.kube/config)",
      "Read(file_path=**/.docker/config.json)",
      "Read(file_path=**/.npmrc)",
      "Read(file_path=**/.pypirc)",
      "Read(file_path=**/.cargo/credentials*)",
      "Read(file_path=**/.git-credentials)",
      "Read(file_path=**/.netrc)",
      "Read(file_path=**/.config/gh/hosts.yml)",
      "Read(file_path=**/.config/gh/config.yml)",
      "Read(file_path=**/.claude/.credentials.json)",
      "Read(file_path=**/.anthropic/**)",
      "Read(file_path=**/.pi/**/auth.json)",
      "Read(file_path=**/.gnupg/**)",
      "Read(file_path=**/.bash_history)",
      "Read(file_path=**/.zsh_history)",
      "Read(file_path=**/.psql_history)",
      "Read(file_path=**/.python_history)",
      "Read(file_path=**/.node_repl_history)",
      "Read(file_path=**/.wget-hsts)",
      "Bash(command=*cat*.env*)",
      "Bash(command=*printenv*)",
      "Bash(command=*inspect*C

Read the full file on GitHub · 163 lines

Changes

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.

2d ago First seen · 163 lines scan C 0307b60a0b9c

Subscribe to this mod's changes

openharness is a settings file published in the GitHub repository mifunedev/openharness (36 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it C with 2 findings (reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Debugging DevOps and cloud LangChain NVIDIA claude-code codex deepagents docker

openharness

Getting it into your agent

Grade C, and why

Reaches for credential fileshighPrivilege escalation

Makes network callslowCapability

How it starts

What this file has done since we first saw it

Other settings, from other repositories

settings

supabase

claude-cookbooks

claude-code-best-practice

electron

uv