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.
npx agentmods add skills/try-works/recursive-mode/recursive-debuggingnpx skills add try-works/recursive-mode --skill recursive-debugginggit clone --depth 1 https://github.com/try-works/recursive-modeWhat 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.
| Model | Per session | Once 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 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- rlm-debugging — 86% identical, 68 lines differ
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 itFix crash on empty inputInvestigate why the API returns wrong dataDo 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];
}
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.
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.
- 2d ago First seen · 500 lines · 70 tokens per session scan A 0a187a95fc3d
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…