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.
npx agentmods add commands/sifxprime/kodelyth-ecc/debug-blitzgit clone --depth 1 https://github.com/sifxprime/kodelyth-eccWrote 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.
[](https://agentmods.dev/commands/sifxprime/kodelyth-ecc/debug-blitz)<a href="https://agentmods.dev/commands/sifxprime/kodelyth-ecc/debug-blitz"><img src="https://agentmods.dev/badge/commands/sifxprime/kodelyth-ecc/debug-blitz.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00032 | $0.00609 |
| Opus 5 | $0.00016 | $0.00304 |
| Sonnet 5 | $0.00006 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
debug-blitz 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/debug-blitz — Parallel Debug Assault
Three debugging specialists attack your problem from different angles simultaneously. The bug that has resisted one approach rarely survives all three.
What Gets Launched in Parallel
| Agent | Focus |
|---|---|
debug-detective |
Traces the explicit error to root cause — stack traces, logs, hypothesis → proof |
silent-failure-hunter |
Finds bugs with no error — swallowed exceptions, bad fallbacks, wrong output |
env-debugger |
Catches environment-layer bugs — env vars, config drift, "works locally" failures |
Usage
/debug-blitz # general debug — all three agents
/debug-blitz "TypeError on line 42" # paste the error — agents use it as starting point
/debug-blitz --ci # focus env-debugger on CI/CD environment
/debug-blitz --prod # production context — incident-commander added
Report Format
## DEBUG BLITZ REPORT
### Root Cause Analysis (debug-detective)
HYPOTHESIS: [most likely cause]
EVIDENCE: [what points to it]
DISPROVEN: [what was ruled out]
FIX: [exact change needed]
### Silent Failures (silent-failure-hunter)
FOUND: [swallowed errors, bad fallbacks]
RISK: [what could be silently wrong]
### Environment (env-debugger)
CONFIG: [mismatches found]
SECRETS: [missing or wrong vars]
DRIFT: [local vs CI vs prod differences]
---
MOST LIKELY CAUSE: [one sentence]
RECOMMENDED FIX: [one action]
When to Use
- Bug has resisted more than 30 minutes of investigation
- "Works on my machine" but fails in CI or prod
- No error thrown but wrong output
- Intermittent failures with no obvious pattern
- A fix was applied but the bug came back
Execute Now
Invoking this command is confirmation to proceed. Execute immediately:
- Extract the error, symptom, or context from
$ARGUMENTS. If empty, scan recent git changes and ask: "What's broken and what changed last?" - Spawn all agents simultaneously with
run_in_background: true:debug-detective— hypothesis-driven root cause analysissilent-failure-hunter— scan for swallowed errors and bad fallbacksenv-debugger— environment and config layer investigation
- Wait for all to complete.
- Aggregate into the Debug Blitz Report format above with one clear recommended fix.
- End with: "Want me to implement the fix?"
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.
- yesterday First seen · 71 lines · 32 tokens per session scan A 5b25913a992a
debug-blitz is a command published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 609 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
toh-help
Display all Toh Framework commands and quick usage guide.
opsx-new
Start a new change using the experimental artifact workflow (OPSX).
research
Delegate a thorough research investigation to the agy:runner subagent.
experiment
Design A/B test with statistical rigor. Usage: /mindforge:experiment [feature] [--metric conversion|engagement|revenue] [--duration 2w].
kimi-setup
Run node "$HOME/.kimi-plugin/kimi-companion.mjs" setup, then report installation and authentication status.
Obad
Search for given words or phrases in the book of Obadiah in one or multiple bibles.