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.
git clone --depth 1 https://github.com/jonathan-vella/apex-acceleratorWrote 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/jonathan-vella/apex-accelerator/apex-debug-log-export)<a href="https://agentmods.dev/commands/jonathan-vella/apex-accelerator/apex-debug-log-export"><img src="https://agentmods.dev/badge/commands/jonathan-vella/apex-accelerator/apex-debug-log-export/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jonathan-vella/apex-accelerator/apex-debug-log-export"><img src="https://agentmods.dev/badge/commands/jonathan-vella/apex-accelerator/apex-debug-log-export.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00038 | $0.05091 |
| Opus 5 | $0.00019 | $0.02545 |
| Sonnet 5 | $0.00008 | $0.01018 |
| Haiku 4.5 | $0.00004 | $0.00509 |
Grade C, and why
apex-debug-log-export scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .apex-logs/_staging How it starts
The opening of the file, as written. The whole thing — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Export Custom-Agent Debug Logs (.apex-logs)
Collect Copilot debug logs from this workspace's active session (and
optionally older sessions / workspace logs), filter the main JSONL stream
down to lines that reference custom agents in .github/agents/,
compress everything into a single .tar.gz archive under .apex-logs/,
and print a manual upload instruction. The prompt never uploads —
you upload to OneDrive yourself via a browser.
Scope
- Output directory:
.apex-logs/at the repo root (gitignored). - Bundle name:
apex-debug-<UTC-timestamp>-<sessionShort>.tar.gz. - Default capture: the most recent non-active Copilot debug-log
directory in this workspace — i.e. the conversation that ran
before this prompt was invoked.
$VSCODE_TARGET_SESSION_LOGpoints at the current prompt's own session, which is almost never what the user wants archived; it is therefore excluded by default and only the user can opt back into it (Step 1). - Opt-in capture: the active prompt session, older sessions in the
same workspace, the active session transcript JSONL, and workspace
logs/copilot/. - Filter source for "custom agent" lines: every agent file path under
.github/agents/*.agent.mdplus the short keys intools/registry/agent-registry.json(agentsmap keys). - Redaction (default on): strip common secret patterns from the filtered JSONL before bundling.
- Never includes
agent-output/,infra/, ornode_modules/.
Inputs
| Variable | Source | Default |
|---|---|---|
| session_dir | user pick (Step 0/1) | most recent non-active session |
| include_older | user choice | no |
| include_xcript | user choice (transcript JSONL) | no |
| include_ws | user choice (logs/copilot/) |
no |
| redact | user choice | yes |
| onedrive_link | argument-hint | none (printed only if given) |
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 · 443 lines · 38 tokens per session scan C 81b23d67fca2
apex-debug-log-export is a command published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 5,091 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other commands, from other repositories
analyze-failures
Triage Katalon True Platform/TestOps test failures and file defects. Use when you need to investigate failed test results, classify each failure as product defect vs automation defect vs environment/data issue, cluster failures by common signature, find likely root cause from execution data, and optionally create…
test-maintenance
Maintain and evolve a Katalon True Platform/TestOps regression suite as the application changes. Use when you need to detect which tests broke or became flaky from stability and result history, diagnose whether a case needs repair vs regeneration, repair test assets (update, move, reorganize cases), refresh coverage…
fix_issue
Use the text the user typed after the command name as the request for this command.
validate_runtime
Use the text the user typed after the command name as the request for this command.
refactor-clean
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
ink-art
Hand-drawn ink-on-white doodle animation — a character that draws itself then walks/dances/waves, or a deadpan contraption explainer. Vector, deterministic, rendered via HyperFrames to MP4.