debug-trace

A guided debugging command that reads an error and traces the code path that led to it.

In plain words
What is it for?
Use it to explain what went wrong, identify supporting evidence, recommend code changes, and suggest tests that could prevent the problem from returning.
Why use it?
It organizes the investigation from the error message to likely root causes, so debugging does not rely on guesswork.

Command

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 commands/armanzeroeight/fastagent-plugins/debug-trace
Clone the repo
git clone --depth 1 https://github.com/armanzeroeight/fastagent-plugins
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 255 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 $0.00010 $0.00255
Opus 5 $0.00005 $0.00128
Sonnet 5 $0.00002 $0.00051
Haiku 4.5 $0.00001 $0.00026

Measured yesterday against content hash 3347b92c1e69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-trace 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 yesterday.

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.

plugins/developer-toolkit/commands/debug-trace.md · 43 lines

What it actually says

Debug Trace Analysis

Investigate the issue: $ARGUMENTS

Analysis Steps

  1. Understand the Error:

    • Parse error message and stack trace
    • Identify failure point
    • Note error type and context
  2. Trace Execution Path:

    • Follow code flow leading to error
    • Identify relevant functions/methods
    • Check variable states and conditions
  3. Form Hypotheses:

    • List possible root causes
    • Prioritize by likelihood
    • Consider recent changes: !git log --oneline -10
  4. Identify Root Cause:

    • Explain what went wrong
    • Explain why it happened
    • Show evidence supporting diagnosis
  5. Suggest Fix:

    • Provide specific code changes
    • Explain why fix works
    • Suggest tests to prevent recurrence

Present findings clearly with:

  • Root cause explanation
  • Evidence (stack trace, code snippets)
  • Recommended fix
  • Prevention strategy
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. yesterday First seen · 43 lines · 10 tokens per session scan A 3347b92c1e69

Subscribe to this mod's changes

debug-trace is a command published in the GitHub repository armanzeroeight/fastagent-plugins (29 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 255 once invoked, about $0.0001 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.