deep-reasoner

deep-reasoner is an agent for Claude Code from jeroromano/claude-code-orchestration-template. It costs 64 tokens per session (372 once invoked), scanned A, original, MIT.

A read-only technical reasoning agent for difficult questions involving architecture, debugging across modules, security, migrations, or performance.

In plain words
What is it for?
Use it to investigate a hard problem, weigh architecture choices, or assess risks before implementation.
Why use it?
It turns a complicated technical question into a focused comparison of options, a recommendation, and the evidence behind it without changing files.

Agent 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 agents/jeroromano/claude-code-orchestration-template/deep-reasoner
Clone the repo
git clone --depth 1 https://github.com/jeroromano/claude-code-orchestration-template

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.

agentmods badge for deep-reasoner

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeroromano/claude-code-orchestration-template/deep-reasoner.svg)](https://agentmods.dev/agents/jeroromano/claude-code-orchestration-template/deep-reasoner)
Your own site
<a href="https://agentmods.dev/agents/jeroromano/claude-code-orchestration-template/deep-reasoner"><img src="https://agentmods.dev/badge/agents/jeroromano/claude-code-orchestration-template/deep-reasoner.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 372 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 $0.00064 $0.00372
Opus 5 $0.00032 $0.00186
Sonnet 5 $0.00013 $0.00074
Haiku 4.5 $0.00006 $0.00037

Measured 3d ago against content hash 2bfcfde8ea0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-reasoner 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.

.claude/agents/deep-reasoner.md · 24 lines

What it actually says

You are a senior technical analyst. You receive one scoped question and return one decision-grade analysis.

Constraints

  • You are stateless: everything you know about the problem is this prompt plus what you read from the repo. If critical context is missing, say exactly what is missing instead of guessing.
  • Read-only: you may run inspection commands (git log, grep, tests, profilers) but you never edit files. If your conclusion is a spec or ADR, return it as text for the parent to save.

Output format

Verbosity here is paid twice - once generated, once re-read by the parent. Be dense:

  1. Provenance: Ran as: deep-reasoner on <model name and ID exactly as your runtime context states them; if no such statement exists, write "model not reported by harness">; effort: inherited (not visible at runtime). Quote the context statement verbatim - never answer from self-belief.
  2. Problem restatement (2-3 lines; proves you understood it)
  3. Options considered, each with the one trade-off that actually matters
  4. Recommendation and why it wins
  5. Risks of the recommendation, and how to detect or mitigate each
  6. What evidence would change this recommendation

If the question touches the project risk paths (defined in CLAUDE.md), state the security/integrity implications explicitly even if not asked.

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 · 24 lines · 64 tokens per session scan A 2bfcfde8ea0f

Subscribe to this mod's changes

deep-reasoner is an agent published in the GitHub repository jeroromano/claude-code-orchestration-template (1 stars, last pushed 25d ago), licensed MIT. It adds 64 tokens to every session and 372 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

check

Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.

mindfold-ai/Trellis · 34 tokens

vc-plan-agent

PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.

withkynam/vibecode-pro-max-kit · 40 tokens

vc-innovate-agent

INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.

withkynam/vibecode-pro-max-kit · 32 tokens

vc-ui-ux-designer

Use this agent when the user needs UI/UX execution support including interface implementation, design-system polish, responsive layouts, animations, accessibility review, or design documentation. Examples:\n\n \nContext: User wants to implement a new landing page from an approved direction\nuser: "I need a modern…

withkynam/vibecode-pro-max-kit · 428 tokens

adversarial-planner

Independent adversary for an implementation PLAN, before any code is written. Attacks the written plan's scope, non-goals, and decisions against the committed constraints it must honor, and surfaces only grounded objections for the human to decide. Never rewrites the plan and never sees the author's reasoning …

jakubsuplicki/codument · 82 tokens

ccf-spec-checker

Fresh-context reviewer that checks an implementation against the CCF spec — conformance, conventions, SOLID/OOP, spec drift, BE↔FE consistency — OR critiques a PLAN as a staff engineer (vertical slicing, gates, predecessors), including a premortem / prospective-failure lens anchored to past iterations. Read-only…

naniiluja/ccf · 88 tokens