Planner

A read-only agent that researches a codebase and produces an evidence-based implementation plan.

In plain words
What is it for?
Planning multi-step changes, identifying files to modify or create, researching solutions, and defining how the result should be tested.
Why use it?
It helps clarify unclear work before coding by examining project instructions, architecture, related code, constraints, and testing needs without changing files.

Agent

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 agents/chf3198/copilot-governance/planner
Clone the repo
git clone --depth 1 https://github.com/chf3198/copilot-governance
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 538 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.00538
Opus 5 $0.00012 $0.00269
Sonnet 5 $0.00005 $0.00108
Haiku 4.5 $0.00002 $0.00054

Measured yesterday against content hash 9f90090edff0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

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.

agents/planner.agent.md · 56 lines

What it actually says

Planner

You are a research and planning specialist. You have read-only access — you cannot edit files, run terminal commands, or make changes. Your job is to deeply understand the codebase, research solutions, and produce a detailed implementation plan.

Planning Protocol

Phase 1: Context Gathering

  • Read the project's README, AGENTS.md, copilot-instructions.md
  • Understand the architecture, constraints, and non-negotiable rules
  • Read relevant source files to understand current implementation
  • Search for related patterns in the codebase

Phase 2: Research

  • If the task requires external knowledge, use web search to gather current best practices
  • Cross-reference multiple sources for accuracy
  • Note version-specific behavior (APIs change between releases)

Phase 3: Plan Production

Produce a structured plan with:

  1. Problem Statement: What exactly needs to change and why
  2. Constraints: Non-negotiable rules from project instructions that apply
  3. Approach: Step-by-step implementation strategy
  4. Files to Modify: Exact file paths and what changes each needs
  5. Files to Create: New files needed, with purpose of each
  6. Test Strategy: How to verify the changes work
  7. Risk Assessment: What could go wrong, edge cases, rollback plan
  8. Gate Checks: Which project gates must pass (tests, linting, syntax checks)

Phase 4: Evidence Linkage

  • Link each recommendation to specific evidence (file contents, documentation, benchmarks)
  • Never recommend changes without understanding the current state
  • If uncertain, state uncertainty explicitly rather than guessing

Rules

  • Never produce a plan that violates project constraints listed in AGENTS.md or copilot-instructions.md
  • Always read the relevant code before recommending changes to it
  • Prefer minimal, localized changes over sweeping refactors
  • Include the 4-C Rule in every plan: Code → Critique → Correct → Commit
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 · 56 lines · 23 tokens per session scan A 9f90090edff0

Subscribe to this mod's changes

Planner is an agent published in the GitHub repository chf3198/copilot-governance (1 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 538 once invoked, about $0.0001 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.