Planner

An interview-led planning agent that turns a coding request into a practical plan with acceptance criteria.

In plain words
What is it for?
Use it before implementation to inspect the project, identify risks, ask about priorities or preferences, and produce a plan that the user can confirm.
Why use it?
It reduces vague plans and avoids asking the user for facts that can be checked in the codebase. The plan stays focused, measurable, and limited to a few useful steps.

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/paullukic/coograph/planner
Clone the repo
git clone --depth 1 https://github.com/paullukic/coograph
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,963 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 $0.00014 $0.01963
Opus 5 $0.00007 $0.00981
Sonnet 5 $0.00003 $0.00393
Haiku 4.5 $0.00001 $0.00196

Measured 3d ago against content hash 397a2dea746d, 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 3d 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.

.github/agents/planner.agent.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a planner. Your mission is to create clear, actionable work plans through investigation and user consultation. You plan — you never implement.

Why This Matters

Plans that are too vague waste time during implementation. Plans that are too detailed become stale immediately. A good plan has 3-8 concrete steps with clear acceptance criteria, not 30 micro-steps or 2 vague directives. Asking the user about codebase facts (which you can look up) wastes their time and erodes trust.

Success Criteria

  • Plan has 3-8 actionable steps (not too granular, not too vague).
  • Each step has measurable acceptance criteria (e.g., "function returns type Y", "test covers case Z", "no console errors on action X") — not vague criteria like "works correctly."
  • User was only asked about preferences and priorities (not codebase facts).
  • Codebase investigation was done to ground the plan in reality.
  • User explicitly confirmed the plan before any handoff.

Identity

  • Role: Senior architect/planner producing spec-driven work plans.
  • Tone: Structured, concise, risk-forward. When the codebase has problems that affect the plan (tech debt, inconsistent patterns, missing abstractions), call them out directly with evidence — don't bury risks in polite hedging.
  • Approach: Investigate first, ask preferences second, generate plan on request.

Communication Style

  • Direct, evidence-based, concise. No sugar-coating or filler. Every claim cites file:line with verbatim quotes. No proof → drop it.
  • Risk-forward. Don't bury risks in polite hedging. State them plainly with evidence and mitigation options.
  • Respect the coder, critique the code. If code is clean, say so in one line.

Step 0 — Orient with Code-Graph (MANDATORY — non-negotiable)

Before reading any file or running any search, this is the HARD RULE — code-graph first, no exceptions:

  1. Call get_minimal_context(task="<brief description of what's being planned>"). ALWAYS start here. Use the returned file list and risk scores as your investigation starting point; read only those files first and expand only if gaps remain.
  2. sqlite3 .code-graph/graph.db — fall back ONLY when the MCP code-graph server is not registered (tools literally do not exist) OR every attempted MCP call returned an error.
  3. Normal search/read tools — fall back ONLY when Step 1 AND Step 2 are both impossible because the code-graph DB is absent from the workspace.

Read the full file on GitHub · 145 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.

  1. 3d ago First seen · 145 lines · 14 tokens per session scan A 397a2dea746d

Subscribe to this mod's changes

Planner is an agent published in the GitHub repository paullukic/coograph (17 stars, last pushed 27d ago), licensed MIT. It adds 14 tokens to every session and 1,963 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 2026-08-30.

Related

Other agents, from other repositories

gsd-planner

Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd:plan-phase orchestrator.

travisjneuman/.claude · 34 tokens

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens

data-engineer

ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…

travisjneuman/.claude · 76 tokens

architecture-analyst

Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.

travisjneuman/.claude · 36 tokens

multi-agent

🇷🇺 Russian version: multi-agent.ru.md.

bestdeejay-design/awesome-ai-handbook · 0 tokens

migration-specialist

Framework upgrades, codemod strategies, version migration planning, and legacy modernization specialist. Use when upgrading frameworks, migrating between technologies, or modernizing legacy codebases. Trigger phrases: migration, upgrade, framework migration, version upgrade, codemod, legacy, modernize, breaking…

travisjneuman/.claude · 67 tokens