delegate-local

A set of agent settings that allows selected test and validation commands and runs a check after files are edited or written.

In plain words
What is it for?
Running the project's tests, checking skill files, evaluating triggers, choosing or auditing models, summarising metrics, and watching GitHub Actions runs.
Why use it?
It limits routine command access to named project checks while automatically validating changes after edits.

Settings file for Claude Code

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/ismaelmartinez/delegate-local/settings
Clone the repo
git clone --depth 1 https://github.com/IsmaelMartinez/delegate-local

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 A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

delegate-local 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 yesterday.

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.

.claude/settings.json · 32 lines

What it actually says

{
  "permissions": {
    "allow": [
      "Bash(bash tests/run-tests.sh)",
      "Bash(bash tests/test-validate-frontmatter.sh)",
      "Bash(bash tests/test-validate-content.sh)",
      "Bash(bash tests/test-delegate.sh)",
      "Bash(bash tests/test-metrics-summary.sh)",
      "Bash(bash scripts/validate-frontmatter.sh *)",
      "Bash(bash scripts/validate-skill-content.sh *)",
      "Bash(bash scripts/eval-skill-triggers.sh)",
      "Bash(bash scripts/audit-models.sh)",
      "Bash(bash scripts/pick-model.sh *)",
      "Bash(bash scripts/metrics-summary.sh *)",
      "Bash(gh run watch *)"
    ]
  },
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "bash .claude/hooks/post-edit-validate.sh"
          }
        ]
      }
    ]
  }
}
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.

  1. yesterday First seen · 32 lines scan A 811f885c92a8

Subscribe to this mod's changes

delegate-local is a settings file published in the GitHub repository IsmaelMartinez/delegate-local (5 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.