deepreason-orchestrator

deepreason-orchestrator is a skill for Claude Code, Codex from AHepi/DeepReason. It costs 46 tokens per session (1,107 once invoked), scanned A, original, MIT.

A controller for work on DeepReason, a project that uses tightly defined stages and recorded evidence to diagnose and fix problems. It routes each task to one specialized step at a time.

In plain words
What is it for?
It helps manage DeepReason goals, require a reproduction before diagnosis, require a diagnosis before a fix, and park unrelated findings for later.
Why use it?
It prevents unrelated work and skipped investigation stages from being mixed into the same task.

Skill for Claude CodeCodex

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 skills/ahepi/deepreason/deepreason-orchestrator
Any agent
npx skills add AHepi/DeepReason --skill deepreason-orchestrator
Clone the repo
git clone --depth 1 https://github.com/AHepi/DeepReason

Made for: Claude Code, Codex.

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 deepreason-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/ahepi/deepreason/deepreason-orchestrator.svg)](https://agentmods.dev/skills/ahepi/deepreason/deepreason-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/ahepi/deepreason/deepreason-orchestrator"><img src="https://agentmods.dev/badge/skills/ahepi/deepreason/deepreason-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,107 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 $0.00046 $0.01107
Opus 5 $0.00023 $0.00553
Sonnet 5 $0.00009 $0.00221
Haiku 4.5 $0.00005 $0.00111

Measured today against content hash b0f863156396, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deepreason-orchestrator 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 today.

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/skills/deepreason-orchestrator/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepReason problem orchestrator

You are running a tightly bounded workflow. You do not freelance. You select ONE subskill, execute it to its exit criteria, then return here to select the next. You never blend phases.

The scope contract (read before every phase)

  1. One tranche = one goal. A tranche works exactly one GOAL.md (produced by dr-set-goal). Anything else you notice goes into PARKED.md — never into your work. Write the parked entry for its FUTURE RUNNER, at park time, while the context is free: one line of WHAT, then a ready-to-send prompt (route, one-goal statement, evidence pointers, end state). Starting the follow-up should cost the operator a paste, not an authoring session.
  2. Evidence over prose. Claims about DeepReason behavior are only admissible if derived from typed records: log.jsonl, objects/, progress.jsonl, run-status.json, REPLAY_VALIDATION.json, verify_root, or test output. Your own summary of what code "probably does" is not evidence.
  3. No phase-skipping. You may not implement without an approved FIX.md. You may not write FIX.md without a DIAGNOSIS.md. You may not write DIAGNOSIS.md without a reproduction or record-derived trace.
  4. Stop conditions. Stop and report (do not improvise) when: a command fails twice the same way; evidence contradicts the goal; the fix requires touching frozen-record semantics (anything under capabilities/state.py digests, harness.py event application, or replay validation record formats); or the diff would exceed ~150 changed lines. Before any stop becomes a question to the operator, load dr-ask-the-right-question: route it to the cheapest authority first, and ask only what survives the dominance test — batched, with a recommendation.

Map and environment preflight (do this before routing, every time)

Full procedure, canonical: dr-drive-harness §1 (session/environment preflight — branch resync, deepreason importable, credential check) and §4 (map preflight — docs/map/INDEX.mdINV-frozen-surfaces.md → seam document → record the resolved ids in GOAL.md). Load it if this session has not run the harness before. Also load pinker-write-for-readers once per session, BEFORE your first message the operator will see (it replaced dr-explain-to-operator on 2026-09-03; CLAUDE.md Conventions state what carries over).

Read the full file on GitHub · 90 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. today Changed · +1 lines b0f863156396
  2. 4d ago First seen · 89 lines · 46 tokens per session scan A 5985bf37b0b4

Subscribe to this mod's changes

deepreason-orchestrator is a skill published in the GitHub repository AHepi/DeepReason (141 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,107 once invoked, about $0.0002 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens