debug

A command for investigating a software bug by reproducing it, narrowing down its cause, applying a small fix, and checking the result.

In plain words
What is it for?
Use it for crashes, incorrect results, stale data, or other repeatable problems, including adding regression tests when appropriate.
Why use it?
It replaces guesswork with a documented debugging process and preserves lessons about known errors.

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/valsecchi75/project-scaffolder/debug
Clone the repo
git clone --depth 1 https://github.com/valsecchi75/project-scaffolder
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 397 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 $0.00033 $0.00397
Opus 5 $0.00016 $0.00198
Sonnet 5 $0.00007 $0.00079
Haiku 4.5 $0.00003 $0.00040

Measured 2d ago against content hash 178b509f858a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug 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.

commands/debug.md · 44 lines

What it actually says

/debug

Structured debugging (Karpathy debug principle). Do NOT guess — reproduce and isolate first.

Usage

/debug <symptom description>

Examples

/debug App crashes when adding a subscription with empty name
/debug DateFormat throws on Android 11 with IT locale
/debug Isar query returns stale data after save

Phases

  1. Reproduce — write exact steps that trigger the bug. Confirm reproducibility.
  2. Isolate — binary-search the cause. Identify the minimum failing case.
  3. Hypothesize — list 2-3 hypotheses, ranked by likelihood.
  4. Diagnose — verify the top hypothesis with evidence (log, stack trace, diff).
  5. Fix — the minimum change that resolves the diagnosed cause.
  6. Verify — re-run repro steps, confirm fixed, add a regression test where appropriate.
  7. Document — atomic operations:
    • Append entry to wiki/debugging/known-errors.md (ID KE-NNN)
    • Append entry to guardrails/errors-to-avoid.md (ID ERR-NNN, cross-referenced to KE-NNN)
    • Call Synapse to propagate the lesson to connected skills

Rules

  • NEVER skip Reproduce. If you can't reproduce, the bug is not understood.
  • Prefer one small fix over a wide refactor.
  • If root cause is shared infrastructure → flag Synapse for multi-skill propagation.
  • If stuck after 3 hypotheses: STOP, ask the user for more context or escalate.
  • Every /debug session ends with either a fix + documentation, or an explicit [INVESTIGATING] entry.
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 · 44 lines · 33 tokens per session scan A 178b509f858a

Subscribe to this mod's changes

debug is a command published in the GitHub repository valsecchi75/project-scaffolder (9 stars, last pushed 29d ago), licensed MIT. It adds 33 tokens to every session and 397 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.