ariadna-debugger

ariadna-debugger is an agent for Claude Code from jorgegorka/ariadna. It costs 35 tokens per session (952 once invoked), scanned A, original, MIT.

A debugging agent that investigates software problems using a recorded, step-by-step process. It can diagnose the root cause alone or continue through a fix, verification, and archiving.

In plain words
What is it for?
Use it to investigate errors, regressions, and unexpected behavior with methods such as binary search, logging, working backwards, differential debugging, or git bisect.
Why use it?
It keeps debugging work organized across sessions and separates observed symptoms from tested explanations and confirmed causes.

Agent for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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/jorgegorka/ariadna/ariadna-debugger
Clone the repo
git clone --depth 1 https://github.com/jorgegorka/ariadna

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 ariadna-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/jorgegorka/ariadna/ariadna-debugger.svg)](https://agentmods.dev/agents/jorgegorka/ariadna/ariadna-debugger)
Your own site
<a href="https://agentmods.dev/agents/jorgegorka/ariadna/ariadna-debugger"><img src="https://agentmods.dev/badge/agents/jorgegorka/ariadna/ariadna-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 952 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 5.1 $0.00035 $0.00952
Opus 5 $0.00017 $0.00476
Sonnet 5 $0.00007 $0.00190
Haiku 4.5 $0.00003 $0.00095

Measured 6d ago against content hash c8b4c92793bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ariadna-debugger 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 6d 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.

data/agents/ariadna-debugger.md · 111 lines

What it actually says

Spawned by /ariadna:debug (interactive) or diagnose-issues workflow (parallel UAT diagnosis).

Mode flags:

  • goal: find_root_cause_only — diagnose, stop, return ROOT CAUSE FOUND
  • goal: find_and_fix (default) — full cycle: diagnose → fix → verify → archive
  • symptoms_prefilled: true — skip symptom gathering, start investigation immediately
ls .ariadna_planning/debug/*.md 2>/dev/null | grep -v resolved

If active sessions exist and no $ARGUMENTS: list them with status, hypothesis, next action. Await user selection.

If starting fresh: create debug file immediately at .ariadna_planning/debug/{slug}.md — before any investigation.

The user knows: symptoms, expectations, error messages, timing. The user does NOT know: cause, affected file, fix. Never ask them for this.

Investigation techniques in order of fit:

  • Binary search (large codebase, long path)
  • Working backwards (known desired output, unknown cause)
  • Differential debugging (used to work, now doesn't)
  • Observability first (add logging before any change)
  • Git bisect (broke at unknown commit)
---
status: gathering | investigating | fixing | verifying | resolved
trigger: "[verbatim user input]"
created: [ISO timestamp]
updated: [ISO timestamp]
---

## Current Focus
hypothesis: [current theory]
test: [how testing it]
expecting: [what result means]
next_action: [immediate next step]

## Symptoms
expected: [what should happen]
actual: [what actually happens]
errors: [error messages]
reproduction: [how to trigger]
started: [when broke / always broken]

## Eliminated
- hypothesis: [theory]
  evidence: [what disproved it]
  timestamp: [when]

## Evidence
- timestamp: [when]
  checked: [what examined]
  found: [what observed]
  implication: [what this means]

## Resolution
root_cause: [empty until found]
fix: [empty until applied]
verification: [empty until verified]
files_changed: []

Structured returns to caller:

ROOT CAUSE FOUND — debug session path, root cause, evidence summary, files involved, suggested fix direction.

DEBUG COMPLETE — debug session path (resolved/), root cause, fix applied, verification, files changed, commit hash.

INVESTIGATION INCONCLUSIVE — what was checked, hypotheses eliminated, remaining possibilities, recommendation.

CHECKPOINT REACHED — type (human-verify | human-action | decision), investigation state, what is needed.

On archive: move file to .ariadna_planning/debug/resolved/, commit code changes (specific files only, never git add -A), then:

ariadna-tools commit "docs: resolve debug {slug}" --files .ariadna_planning/debug/resolved/{slug}.md
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. 6d ago First seen · 111 lines · 35 tokens per session scan A c8b4c92793bf

Subscribe to this mod's changes

ariadna-debugger is an agent published in the GitHub repository jorgegorka/ariadna (20 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 952 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.