dr-diagnose

dr-diagnose is a skill for Claude Code, Codex from AHepi/DeepReason. It costs 46 tokens per session (1,617 once invoked), scanned A, original, MIT.

A skill for finding the main cause of a DeepReason defect from its typed investigation record, rather than starting with code inspection. It reads the relevant map's recorded warnings first and produces a DIAGNOSIS.md file with one cause and supporting evidence.

In plain words
What is it for?
Use it after GOAL.md exists to investigate a failed or suspicious DeepReason run and document the primary cause with evidence pointers.
Why use it?
It focuses the investigation on recorded evidence and known failure patterns, while avoiding code changes during diagnosis.

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/dr-diagnose
Any agent
npx skills add AHepi/DeepReason --skill dr-diagnose
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 dr-diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/ahepi/deepreason/dr-diagnose.svg)](https://agentmods.dev/skills/ahepi/deepreason/dr-diagnose)
Your own site
<a href="https://agentmods.dev/skills/ahepi/deepreason/dr-diagnose"><img src="https://agentmods.dev/badge/skills/ahepi/deepreason/dr-diagnose.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 1,617 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 $0.01617
Opus 5 $0.00023 $0.00809
Sonnet 5 $0.00009 $0.00323
Haiku 4.5 $0.00005 $0.00162

Measured today against content hash 76f95e71f643, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dr-diagnose 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/dr-diagnose/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnose from the record

Input: GOAL.md. Output: DIAGNOSIS.md naming ONE primary cause. You read the record first and the code second. You change nothing.

Step 1 — run the stop report, and open DIAGNOSIS.md with it

Run this before reading any code, any log, and any run-config file:

deepreason stop-report <root-or-home>

Paste its section 4 (THE STOP, CLASSIFIED) verbatim as the FIRST section of DIAGNOSIS.md, before writing anything of your own. Cite a report line by section number for every claim naming a defect, a seat, or a model as the cause.

GATE, run before you commit DIAGNOSIS.md:

grep -q "THE STOP, CLASSIFIED" DIAGNOSIS.md

Exit 0 = pass. Exit 1 = the phase is not-done; STOP and report that.

The report accepts three source kinds, so a run that never opened a log still has one: a run root, a run directory that compiled a manifest and failed its qualification gate (root-no-log), and a home whose qualification is cached (home-no-root).

When the failure has no run root and no home at all — a smoke harness, a build, a tool — write one line in DIAGNOSIS.md naming which of the three kinds was absent, and paste that instrument's own typed failure envelope in place of section 4. The GATE above still applies to everything else.

Outlets, one per prohibition:

You cannot... Then
produce the report STOP; report not-done with the command's stderr
cite a report line for a cause PARK the hypothesis; diagnose what you can cite
find any typed source paste the instrument's failure envelope, and say which kind was absent

This displaces the old ordering, in which run-status.json and REPLAY_VALIDATION.json were rows 1 and 4 of "Where the truth lives" and each reader re-derived them by hand. The report derives all of it, plus the qualification rows and provider health that hand-reading skipped. Those rows below are now the DEEPER DIVE, entered after the report names a box.

Read the map's Traps SECOND — it is cheaper than the record

Read the full file on GitHub · 146 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 · +50 lines 76f95e71f643
  2. 4d ago First seen · 96 lines · 46 tokens per session scan A b88b32b171e1

Subscribe to this mod's changes

dr-diagnose 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 1,617 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