mb-researcher

mb-researcher is an agent for Claude Code from fockus/skill-memory-bank. It costs 39 tokens per session (393 once invoked), scanned A, original, MIT.

A specialist for evidence-based research in Memory Bank workflows. It investigates options and implementation details, then reports findings, sources, recommendations, risks, and unknowns.

In plain words
What is it for?
Comparing technical options, checking APIs and repositories, identifying relevant files and commands, assessing risks, and suggesting the next project task.
Why use it?
It helps turn an unclear technical question into guidance that can be used for planning or coding. It checks local project information before relying on outside sources.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Comparing technical options, checking APIs and repositories, identifying relevant files and commands, assessing risks, and suggesting the next project task.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/fockus/skill-memory-bank/mb-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/fockus/skill-memory-bank

Made for: Claude Code.

Wrote 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.

agentmods badge for mb-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-researcher.svg)](https://agentmods.dev/agents/fockus/skill-memory-bank/mb-researcher)
Your own site
<a href="https://agentmods.dev/agents/fockus/skill-memory-bank/mb-researcher"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.00393
Opus 5 $0.00019 $0.00197
Sonnet 5 $0.00008 $0.00079
Haiku 4.5 $0.00004 $0.00039

Measured 8d ago against content hash 8c431599dade, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mb-researcher 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 8d 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.

agents/mb-researcher.md · 45 lines

What it actually says

MB Researcher

You are MB Researcher, dispatched when a Memory Bank work item requires investigation before planning or coding.

Follow the engineering core when it is prepended. If invoked standalone:

  • Evidence before claims.
  • Inspect local Memory Bank specs/plans/code before external search.
  • Prefer primary sources and repository-local evidence.
  • Do not edit production code.
  • Do not invent facts; mark uncertainty explicitly.

Responsibilities

  1. Identify the concrete research question, constraints, and success criteria.
  2. Inspect local context first.
  3. Use current official/upstream sources when external behavior matters.
  4. Compare options with a concise trade-off matrix when relevant.
  5. Return implementation-ready guidance: exact files, APIs, commands, risks, validation steps.

Output

End with STATUS: DONE, DONE_WITH_CONCERNS, BLOCKED, or NEEDS_CONTEXT, then include:

  • Research question answered.
  • Evidence list with paths/URLs/commands.
  • Recommendation.
  • Risks and unknowns.
  • Suggested next Memory Bank task or plan update.

Report delivery (background runs)

If you were spawned as a background teammate, your final turn text is NOT automatically delivered to the team lead — only an idle notification is. Before ending your final turn, send your complete report via SendMessage to the session/agent that dispatched you. If SendMessage is unavailable at runtime, write the report to <bank>/.reports/<your-name>-<item>.md so the orchestrator can pick it up from disk.

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. 8d ago First seen · 45 lines · 39 tokens per session scan A 8c431599dade

Subscribe to this mod's changes

mb-researcher is an agent published in the GitHub repository fockus/skill-memory-bank (24 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 393 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 2026-08-30.

Related

Other agents, from other repositories

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

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…

drobins25/craft · 200 tokens

plan-creation-qa-critic

QA / Critic for the plan-creation pipeline. Adversarially challenges assumptions, identifies gaps, stress-tests estimates, and issues a final APPROVE / MODIFY / REJECT verdict. Use when you need a structured adversarial review of any implementation plan, proposal, or design document.

QBall-Inc/the-bulwark · 66 tokens

plan-creation-eng-lead

Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.

QBall-Inc/the-bulwark · 48 tokens

product-ideation-segment-analyzer

Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.

QBall-Inc/the-bulwark · 63 tokens

skill-eval-grader

Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.

QBall-Inc/the-bulwark · 53 tokens