recursive-debugging

A structured debugging step for recursive-mode coding tasks that investigates the root cause of a bug, failed test, crash, or other unexpected behavior before changes are made.

In plain words
What is it for?
Use it to investigate failing tests, crashes, wrong results, performance problems, and integration issues by finding the underlying cause first.
Why use it?
It reduces guesswork and prevents symptom-only fixes that can create new bugs or require repeated rework.

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/try-works/recursive-mode/recursive-debugging
Any agent
npx skills add try-works/recursive-mode --skill recursive-debugging
Clone the repo
git clone --depth 1 https://github.com/try-works/recursive-mode

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,461 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 $0.00070 $0.03461
Opus 5 $0.00035 $0.01731
Sonnet 5 $0.00014 $0.00692
Haiku 4.5 $0.00007 $0.00346

Measured 2d ago against content hash 0a187a95fc3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recursive-debugging 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/recursive-debugging/SKILL.md · 500 lines

How it starts

The opening of the file, as written. The whole thing — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.

recursive-debugging (Phase 1.5)

Overview

When a requirement involves fixing a bug or investigating unexpected behavior, ad-hoc fixes waste time and create new bugs. Systematic debugging finds the root cause before any fix is attempted.

Core Principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure.

The Iron Law for recursive-mode debugging:

NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST

Trigger examples

  • Tests are failing after the last change; debug it
  • Fix crash on empty input
  • Investigate why the API returns wrong data
  • Do a root cause analysis before making changes

When to Use

Mandatory Phase 1.5 when:

  • Requirement is a bug fix
  • Test failures need investigation
  • Unexpected behavior reported
  • Performance problems
  • Integration issues

Use ESPECIALLY when:

  • Under time pressure (emergencies make guessing tempting)
  • "Just one quick fix" seems obvious
  • Previous fix attempts failed
  • You don't fully understand the issue

Don't skip when:

  • Issue seems simple (simple bugs have root causes too)
  • You're in a hurry (rushing guarantees rework)
  • Manager wants it fixed NOW (systematic is faster than thrashing)

Phase 1.5 Insertion

Phase 1.5 is inserted between Phase 1 (AS-IS) and Phase 2 (TO-BE Plan) when debugging is required:

Phase 0: 00-requirements.md
    ->
Phase 1: 01-as-is.md (captures current behavior)
    ->
Phase 1.5: 01.5-root-cause.md <- NEW (this skill)
    ->
Phase 2: 02-to-be-plan.md (includes fix plan based on root cause)

The Four Phases of Systematic Debugging

digraph debugging_phases {
    rankdir=TB;
    
    phase1 [label="Step 1:\nRoot Cause Investigation", shape=box, style=filled, fillcolor="#ffcccc"];
    phase2 [label="Step 2:\nPattern Analysis", shape=box, style=filled, fillcolor="#ffffcc"];
    phase3 [label="Step 3:\nHypothesis & Testing", shape=box, style=filled, fillcolor="#ccffcc"];
    phase4 [label="Step 4:\nFix Implementation", shape=box, style=filled, fillcolor="#ccccff"];
    
    phase1 -> phase2 -> phase3 -> phase4;
    
    // Feedback loops
    phase3 -> phase1 [label="hypothesis\nfailed", style=dashed];
    phase4 -> phase1 [label="fix\nfailed", style=dashed];
}

Read the full file on GitHub · 500 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 500 lines · 70 tokens per session scan A 0a187a95fc3d

Subscribe to this mod's changes

recursive-debugging is a skill published in the GitHub repository try-works/recursive-mode (129 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 3,461 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 2026-08-30.

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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens