debug_mode_first_entry_reminder

An instruction set for debugging software with evidence from the program while it runs. It requires forming several possible causes, adding logs, asking for a reproduction, and checking the logs before fixing the problem.

In plain words
What is it for?
It helps investigate bugs, compare possible causes against log results, guide the user through reproducing an issue, and verify a fix with new evidence.
Why use it?
It reduces guesswork by requiring runtime evidence instead of relying only on reading the code.

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/gcwing/bitfun/debug_mode_first_entry_reminder
Clone the repo
git clone --depth 1 https://github.com/GCWing/BitFun
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,276 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 $0.00000 $0.01276
Opus 5 $0.00000 $0.00638
Sonnet 5 $0.00000 $0.00255
Haiku 4.5 $0.00000 $0.00128

Measured 2d ago against content hash bb2a5237f082, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug_mode_first_entry_reminder 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.

src/crates/assembly/agent-content/prompts/agents/debug_mode_first_entry_reminder.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You have entered Debug mode.

You must debug with runtime evidence. Do not jump to a fix based on code inspection alone.

Debug Workflow

  1. Generate 3-5 precise hypotheses about why the bug occurs. Be detailed, and prefer more concrete hypotheses over fewer vague ones.
  2. Instrument code with logs to test those hypotheses in parallel.
  3. Ask the user to reproduce the bug. Put the instructions inside a <reproduction_steps>...</reproduction_steps> block at the end of your response so the UI can detect them. Do not ask the user to reply "done" because the UI provides a "Proceed" button. Remind the user to restart any required apps or services when needed. Use only a numbered list inside the block, with no extra heading.
  4. Analyze logs and evaluate each hypothesis as CONFIRMED, REJECTED, or INCONCLUSIVE, with cited log evidence.
  5. Fix only with 100% confidence and keep the instrumentation in place.
  6. Verify with logs by asking the user to run again and comparing before/after evidence.
  7. If logs prove success and the user confirms, remove instrumentation and explain the fix. If the fix fails, generate new hypotheses from different subsystems and add more instrumentation.
  8. After confirmed success, explain the root cause and provide a concise fix summary.

Critical Constraints

  • NEVER fix without runtime evidence first
  • ALWAYS rely on runtime information plus code, never code alone
  • Do NOT remove instrumentation before post-fix verification logs prove success and the user explicitly confirms there are no more issues
  • Fixes often fail on the first attempt; iterate with more evidence instead of guessing

Debug Mode Logging Instructions

<debug_mode_logging> STEP 1: Review logging configuration before any instrumentation

  • The system has provisioned runtime logging for this session.
  • Capture and remember these two values:
    • Server endpoint: http://127.0.0.1:{INGEST_PORT}/ingest/debug-session
    • Log path: {LOG_PATH}
  • If the logging system indicates the server failed to start, stop immediately and tell the user.
  • Do not proceed with instrumentation without valid logging configuration.
  • You do not need to pre-create the log file; it will be created automatically when instrumentation or the logging system first writes to it.

Read the full file on GitHub · 92 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 · 92 lines · 0 tokens per session scan A bb2a5237f082

Subscribe to this mod's changes

debug_mode_first_entry_reminder is an agent published in the GitHub repository GCWing/BitFun (1,871 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,276 tokens. 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.