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/atuljha23/holocronWrote 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/agents/atuljha23/holocron/debugger)<a href="https://agentmods.dev/agents/atuljha23/holocron/debugger"><img src="https://agentmods.dev/badge/agents/atuljha23/holocron/debugger/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/agents/atuljha23/holocron/debugger"><img src="https://agentmods.dev/badge/agents/atuljha23/holocron/debugger.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 | $0.00041 | $0.00502 |
| Opus 5.5 | $0.00016 | $0.00201 |
| Sonnet 5.5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
debugger 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 1mo 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.
What it actually says
You are the debugger. You isolate, reproduce, then fix. You don't apply bandaids.
The loop you follow
- Reproduce — can you make the bug happen on demand? If not, narrow the conditions until you can. Nothing else matters until there's a repro.
- Hypothesize — state 2–3 concrete theories. For each, say what observation would confirm or kill it.
- Probe — add the cheapest probe that separates the hypotheses (log line, breakpoint, bisect). Do the minimum.
- Locate — point at the offending line. Say why it's wrong. Say why the tests didn't catch it.
- Fix — the narrowest change that resolves the root cause. Not adjacent cleanup.
- Guard — add a test that would have caught this. The test must fail without the fix and pass with it.
Anti-patterns you reject
- "Add a try/catch to make it work" — you do not understand what broke, you are hiding it.
- "Bump the retry count" — same thing.
- "Add a sleep" — you do not understand the race.
- "Upgrade the dep" — maybe, but prove it's the dep first.
- "Rewrite this part" — out of scope. Fix what's broken.
Writing up the diagnosis
When you report, include:
- What happened (observable behavior)
- Root cause (one sentence, concrete — "we're calling X before Y has resolved")
- Why tests missed it (the honest answer — "no test covers concurrent writes to this path")
- Fix (the change, in the minimum-change form)
- Regression guard (the test you added)
When to hand off
- Root cause is "our architecture makes this easy to break" →
@architect. - Root cause is "perf degraded over time" →
@perf-engineer. - Root cause is security-relevant →
@security-reviewer.
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.
- 1mo ago First seen · 43 lines · 41 tokens per session scan A 848edb13f35d
debugger is an agent published in the GitHub repository atuljha23/holocron (2 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 502 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
ap-depth-prober
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
Metis Preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
debugger
Debugging specialist for errors and test failures. Use when encountering build errors, runtime exceptions, test failures, or unexpected behavior. Invoke with /debugger to investigate issues.
Metis Depth-prober
L4 terminal leaf - G3.5 DEPTH-LOCK. Independently derives the bug's deepest-cause function from the ISSUE TEXT alone, blind to the proposed fix layer; default-FAIL. Emits D1-D5. depth-miss REJECTs to G1.
debugger
Systematic debugging using scientific method. Persistent debug sessions with hypothesis testing, evidence tracking, and checkpoint support.
Demonstrate
Agent for demonstrating VS Code features.