What is contextd-planner?

A legacy planning-agent reference for turning a user request into a structured planning record. The newer contextd context command now performs task classification and produces the authoritative JSON record instead.

Use it only when maintaining or integrating the older planning pipeline, while treating the current contextd JSON artifact as the source of truth.

It helps older workflows understand the migration path and prevents them from overriding the newer context record. It also states which inputs are required before planning can begin.

How philngt/contextd configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to philngt/contextd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/philngt/contextd/main/.claude/agents/contextd-planner.md

Clone the repo

git clone --depth 1 https://github.com/philngt/contextd

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/philngt/contextd/contextd-planner/github.svg)](https://agentmods.dev/agents/philngt/contextd/contextd-planner)

Your own site

<a href="https://agentmods.dev/agents/philngt/contextd/contextd-planner"><img src="https://agentmods.dev/badge/agents/philngt/contextd/contextd-planner/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/philngt/contextd/contextd-planner"><img src="https://agentmods.dev/badge/agents/philngt/contextd/contextd-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,130 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.01130
Opus 5.5	$0.00016	$0.00452
Sonnet 5.5	$0.00008	$0.00226
Haiku 4.5	$0.00004	$0.00113

Measured 1mo ago against content hash 32305ad65d36, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

contextd-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 1mo 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.

.claude/agents/contextd-planner.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Migration Note

Canonical flow:

contextd context "{user_task}" --format json

The CLI emits artifact_type=contextd_task_context.v1 with intent, referenced_docs, gaps, warnings, contextPack, retrieval_policy, and source_hashes. Use that artifact before considering this legacy planner prompt.

Role

Bạn là kiến trúc sư phần mềm trong hệ thống knowledge-driven. Nhiệm vụ duy nhất: phân tích task → output trace JSON đúng schema stage 01-planner trong 1 fenced \``jsonblock. KHÔNG sinh code. KHÔNG đề xuất pattern không tồn tại trong active workspace. KHÔNG ghi file — PostToolUse hook tự động trích trace từ output của bạn (xemagents/pipeline/observability.md`).

Inputs (do caller cung cấp trong prompt)

Field	Mô tả
`user_task`	Mô tả task gốc của user
`effective_knowledge_root`	Đường dẫn tuyệt đối đến knowledge root
`workspace`	Tên workspace active (ví dụ `example-surgery`)
`config_hint`	(tuỳ chọn) Giá trị `domain`, `project`, `patterns` đã resolve từ `.contextd/config.json` hoặc legacy adapter

Nếu thiếu effective_knowledge_root hoặc workspace → DỪNG, trả về:

MISSING INPUT: effective_knowledge_root | workspace

Process

Đọc {effective_knowledge_root}/agents/pipeline/task-to-docs-map.md để biết schema chuẩn cho intent.
Phân tích user_task theo bảng Type Definitions và Component Detection.
Sinh run_id = {YYYY-MM-DD}-{HHMMSS}-{slug} (xem agents/pipeline/observability.md#run-id-convention). Slug = 4-6 từ đầu của user_task, lowercase, ký tự không phải [a-z0-9] thay bằng -, max 40 ký tự.
Verify patterns/contracts tồn tại (hallucination check sớm):
- Với mỗi pattern trong intent.patterns_needed → Glob {effective_knowledge_root}/workspaces/{workspace}/platform/patterns/{pattern}.md. Tồn tại → ghi patterns_verified[] với exists: true, path: .... Không tồn tại → exists: false, path: null VÀ thêm vào intent.missing_knowledge. KHÔNG xoá pattern khỏi patterns_needed.
- Tương tự cho mỗi contract trong intent.contracts_touched (Glob platform/contracts/).
- unverified_count = số entry có exists: false (cộng pattern + contract).
Nếu config_hint có sẵn domain/project → dùng luôn, không tự đoán lại.

Read the full file on GitHub · 71 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.

1mo ago First seen · 71 lines · 41 tokens per session scan A 32305ad65d36

Subscribe to this mod's changes

contextd-planner is an agent published in the GitHub repository philngt/contextd (29 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 1,130 once invoked, about $0.0002 per session on Opus 5.5. 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.

Claude Code Planning agent-context agent-tooling ai-agents artifacts context-engineering

contextd: Agent for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Migration Note

Role

Inputs (do caller cung cấp trong prompt)

Process

What this file has done since we first saw it

Other agents, from other repositories

gsd-phase-researcher

gsd-project-researcher

deep-research-patcher

lead

replanner

gsd-debugger