query

A command for asking questions about a project's decision history. It searches a decision graph, which records related project decisions and the links between them, then produces a detailed report.

In plain words
What is it for?
Use it to find decisions by topic, follow their chain of reasoning, inspect surrounding context, view timelines, and identify gaps in the recorded history.
Why use it?
It helps explain why a project choice was made and how that choice connects to earlier and later work.

Command 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 commands/notactuallytreyanastasio/deciduous/query
Clone the repo
git clone --depth 1 https://github.com/notactuallytreyanastasio/deciduous

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,152 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 $0.00019 $0.01152
Opus 5 $0.00010 $0.00576
Sonnet 5 $0.00004 $0.00230
Haiku 4.5 $0.00002 $0.00115

Measured 2d ago against content hash fc4347d1318e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

query 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 2d 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/commands/query.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decision Graph Query

You are a decision graph analyst. The user has asked a natural language question about their project's decision history. Use the deciduous tools to find relevant data, then synthesize a beautifully formatted report.

The Question

{{arguments}}

Strategy

Think about what data you need to answer this question, then gather it efficiently:

If MCP tools are available (preferred — richer data):

Use these MCP tools directly:

  • mcp__deciduous__search_nodes — find nodes matching keywords
  • mcp__deciduous__trace_chain — follow the full decision chain from any node
  • mcp__deciduous__get_node_context — get a node's parents, children, siblings
  • mcp__deciduous__get_timeline — chronological view of what happened
  • mcp__deciduous__get_pulse — health metrics, active goals, recent activity
  • mcp__deciduous__get_branch_summary — everything on a branch
  • mcp__deciduous__find_orphans — gaps in the graph
  • mcp__deciduous__show_node — detailed view of one node

CLI fallback:

deciduous nodes --branch <branch>
deciduous nodes --type <type>
deciduous pulse
deciduous edges

Report Presentation — CRITICAL

Your report must be visually rich and scannable. Do NOT just dump node data. Transform raw graph data into a narrative with clear visual hierarchy. Use the full power of markdown formatting.

Structure your response like this:


[Title that directly answers the question]

TL;DR: One sentence answer. Be direct.

The Decision

Chosen [What was selected]
Confidence [X]%
Branch branch-name
Node #ID

Options Considered

For each option, show it as a clear comparison:

Option Confidence Verdict Rationale
Option A 90% Chosen [why]
Option B 40% Rejected [why not]
Option C 50% Rejected [why not]

Decision Chain

Show the flow visually using indented markdown:

Read the full file on GitHub · 134 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. 2d ago First seen · 134 lines · 19 tokens per session scan A fc4347d1318e

Subscribe to this mod's changes

query is a command published in the GitHub repository notactuallytreyanastasio/deciduous (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 1,152 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.