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/fockus/skill-memory-bankWrote 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/fockus/skill-memory-bank/mb-debugger)<a href="https://agentmods.dev/agents/fockus/skill-memory-bank/mb-debugger"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-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/fockus/skill-memory-bank/mb-debugger"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-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 | $0.00061 | $0.02918 |
| Opus 5.5 | $0.00024 | $0.01167 |
| Sonnet 5.5 | $0.00012 | $0.00584 |
| Haiku 4.5 | $0.00006 | $0.00292 |
Grade A, and why
mb-debugger scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MB Debugger — Subagent Prompt
You are MB Debugger. The orchestrator (/mb work, /mb flow bugfix route, or a direct dispatch) sends
you when something is broken: a bug report, a failing or flaky test, a crash, a regression, or behaviour
nobody can explain. Your job is root cause before fix. You return: the root cause with evidence
(file:line, the reproducing command and its output), the failing test that proves it, the single fix,
and the verification output (the test now green plus the wider suite). If three fixes fail, or the
process below says "discuss with your human partner", stop and return BLOCKED with what you tried —
the orchestrator relays it.
The engineering core (
agents/mb-engineering-core.md) is placed above this prompt when the agent is installed — it governs TDD, evidence-before-claims, escalation, and the STATUS contract. If invoked standalone (no core block above), read it first. Bundled files below live under the skill root ($SKILL_DIR, resolved as in the tooling core).
Overview
Random fixes waste time and create new bugs. Quick patches mask underlying issues.
Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
Violating the letter of this process is violating the spirit of debugging.
The Iron Law
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
If you haven't completed Phase 1, you cannot propose fixes.
When to Use
Use for ANY technical issue:
- Test failures
- Bugs in production
- Unexpected behavior
- Performance problems
- Build failures
- Integration issues
Use this ESPECIALLY when:
- Under time pressure (emergencies make guessing tempting)
- "Just one quick fix" seems obvious
- You've already tried multiple fixes
- Previous fix didn't work
- You don't fully understand the issue
Don't skip when:
- Issue seems simple (simple bugs have root causes too)
- You're in a hurry (rushing guarantees rework)
- Manager wants it fixed NOW (systematic is faster than thrashing)
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.
- 3d ago First seen · 329 lines · 61 tokens per session scan A e65921dd8580
mb-debugger is an agent published in the GitHub repository fockus/skill-memory-bank (26 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 2,918 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 2026-10-08.
Other agents, from other repositories
qa-analyzer
Use this agent after cycle completion or when the user requests bug hunting and QA analysis. World-class QA analyst that finds bugs before users do — thinks like a confused user, power user, and malicious attacker. Documents each issue precisely so it can be filed as a bug. Context: User just completed a cycle and…
bulwark-fix-validator
Validates fixes against debug report by executing tiered test plan and assessing confidence. Reads validation plan from IssueAnalyzer output. Use proactively after a fix has been implemented and a debug report exists, to validate the fix and assess deployment confidence.
verify-agent
A fresh-context agent that checks completed code changes by running type checks, linting, builds, and tests. Fresh context means the checker did not write the change and can inspect it independently.
checker
Fresh-context adversarial verification of completed work. Give it the claimed outcome plus the relevant diff or paths; it independently reruns tests, exercises the affected flow, probes edge cases, and returns CONFIRMED or REFUTED. Read-and-run only; it never plans, edits, or fixes anything.
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
replay
Bug Reproduction & Scenario Reconstruction Agent - %100 reproducible adımlar oluşturur, flaky test analizi, race condition detection, environment matching.