planner

Project settings that run automatic shell commands when a coding session starts, stops, or is about to shorten its stored context.

In plain words
What is it for?
Use them to display registry.yaml and available project commands at startup, remind the agent to update session.md, and show a context-compaction reminder.
Why use it?
They remind the agent to load the project's current state, follow its instructions, and record progress before a session ends or context is reduced.

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/nickmisasi/planner/settings
Clone the repo
git clone --depth 1 https://github.com/nickmisasi/planner

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

planner 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 · 38 lines

What it actually says

{
  "hooks": {
    "SessionStart": [
      {
        "matcher": "",
        "hooks": [
          {
            "type": "command",
            "command": "echo '=== PLANNING REPO SESSION START ===' && echo '' && echo 'Reading registry.yaml for current project state:' && echo '' && cat registry.yaml && echo '' && echo '---' && echo 'IMPORTANT: Read CLAUDE.md for full instructions. If the user wants to continue work, use the /continue skill. Available skills: /new-project, /new-idea, /continue, /iterate, /research, /spike, /export, /status'"
          }
        ]
      }
    ],
    "Stop": [
      {
        "matcher": "",
        "hooks": [
          {
            "type": "command",
            "command": "echo 'REMINDER: If you were working on an idea, ensure session.md has been updated with current progress, decisions, open questions, and next steps before ending this session.'"
          }
        ]
      }
    ],
    "PreCompact": [
      {
        "matcher": "",
        "hooks": [
          {
            "type": "command",
            "command": "echo '=== CONTEXT COMPACTION REMINDER ===' && echo '' && echo 'This is an AI-first planning repository. Key files:' && echo '- CLAUDE.md: Full agent instructions' && echo '- registry.yaml: Master project index' && echo '- .claude/skills/: Slash command definitions' && echo '' && echo 'Current registry state:' && cat registry.yaml && echo '' && echo 'Available skills: /new-project, /new-idea, /continue, /iterate, /research, /spike, /export, /status'"
          }
        ]
      }
    ]
  }
}
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 · 38 lines scan A 1a46e35747e2

Subscribe to this mod's changes

planner is a settings file published in the GitHub repository nickmisasi/planner (5 stars, last pushed 4mo 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.