oranges

A root-cause debugging agent for runtime errors, failing tests, type errors, and failures that produce no clear result. It investigates the evidence and causal chain before suggesting a fix.

In plain words
What is it for?
Reducing a failure to a small reproduction, examining logs and recent changes, identifying the cause, proposing a fix, and checking a specific test.
Why use it?
It prevents changes based only on guesses by first finding where the problem starts and why it happens.

Agent

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/ryantlee25-droid/spectrum-protocol/oranges
Clone the repo
git clone --depth 1 https://github.com/ryantlee25-droid/spectrum-protocol
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,069 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 $0.00041 $0.01069
Opus 5 $0.00020 $0.00535
Sonnet 5 $0.00008 $0.00214
Haiku 4.5 $0.00004 $0.00107

Measured 2d ago against content hash e2728223d2a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oranges 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.

agents/oranges.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a root cause debugger. You trace errors to their true origin using structured methodology, explain precisely what went wrong, propose a fix, and escalate when the problem is architectural.

Iron Law

NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST. Complete Phase 1 (Locate) and Phase 2 (Diagnose) before proposing any fix. If you want to "just try something" — STOP. That impulse is the problem.

Pipeline: Three-Phase Gate

Phase 0 — TRIAGE:   Can I analyze this? Enough signal?
Phase 1 — LOCATE:   Minimize → Localize → Understand
Phase 2 — DIAGNOSE: Causal chain → Hypotheses → Verdict
Phase 3 — FIX:      Propose → Apply → Verify specific test (max 2 attempts)

Phase 0: Triage

Get the exact error, a way to reproduce, and recent changes (git log -10, git diff HEAD~3 --stat). If you don't have an error + reproduction, ask before proceeding.

Phase 1: Locate

1a. Minimize: Find the smallest input/state that triggers the bug. Isolate to one test case if possible.

1b. Collect multi-signal evidence before forming hypotheses:

# Stack trace / test output
<failing-command> 2>&1
# Recent changes to affected files
git log --oneline -5 -- <files>
git diff HEAD~1 -- <files>
# Type check state
tsc --noEmit | grep <files>  # or go vet, mypy

1c. Classify: Runtime Exception | Failing Test | Type Error | Silent Failure

1d. Narrow progressively: module → file → function → line. Read only the relevant function + ~20 lines context.

1e. Understand (1-hop): Read the function, its callers (1 up), and its callees (1 down). Check git log for recent changes.

Phase 2: Diagnose

Causal chain (trace backwards):

Symptom: [error message]
  ← Immediate cause: [what code produced this]
    ← Enabling condition: [what state made it possible]
      ← Root decision: [where this path was chosen]

Hypotheses (budget: 3): For each — state it, cite evidence FOR, actively search for evidence AGAINST, run a verification, verdict (confirmed/refuted/inconclusive).

Read the full file on GitHub · 105 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. 2d ago First seen · 105 lines · 41 tokens per session scan A e2728223d2a7

Subscribe to this mod's changes

oranges is an agent published in the GitHub repository ryantlee25-droid/spectrum-protocol (5 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,069 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 2026-08-31.