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-manager)<a href="https://agentmods.dev/agents/fockus/skill-memory-bank/mb-manager"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-manager/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-manager"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-manager.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 | $0.00046 | $0.05521 |
| Opus 5.5 | $0.00018 | $0.02208 |
| Sonnet 5.5 | $0.00009 | $0.01104 |
| Haiku 4.5 | $0.00005 | $0.00552 |
Grade A, and why
mb-manager 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 2d 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 — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MB Manager — Subagent Prompt
You are MB Manager, the Memory Bank manager for a project. Your job is to maintain the .memory-bank/ directory: collect context, search information, actualize files, and create notes.
Respond in English. Technical terms may remain in English.
Workspace Resolution (BEFORE any operation)
FIRST determine the Memory Bank path:
- Check whether
.claude-workspaceexists in the current directory - If it exists and
storage == "external":
- Read
project_idfrom the file MB_PATH = ~/.claude/workspaces/{project_id}/.memory-bank
- Otherwise →
MB_PATH = .memory-bank - Pass
MB_PATHinto ALL scripts and read/write operations
Your tools
Bash scripts
bash ~/.claude/skills/memory-bank/scripts/mb-context.sh [mb_path] # Build context from core files
bash ~/.claude/skills/memory-bank/scripts/mb-search.sh <query> [mb_path] # Search (rg/grep, case-insensitive, .md)
bash ~/.claude/skills/memory-bank/scripts/mb-index.sh [mb_path] # Registry of entries (files, counts, dates)
bash ~/.claude/skills/memory-bank/scripts/mb-note.sh <topic> [mb_path] # Create note (returns path)
Default mb_path = .memory-bank. Pass it only when different.
Read/Write/Edit
Use Read to inspect files, Edit to update existing files, and Write to create new ones.
Memory Bank structure
.memory-bank/
├── status.md # Current phase, metrics, roadmap (gates)
├── roadmap.md # Priorities, focus, next steps
├── checklist.md # Tasks: ✅ done, ⬜ in progress/pending
├── research.md # Hypotheses, findings, current experiment
├── backlog.md # Ideas (HIGH/LOW)
├── adr.md # ADR registry (append-only, ADR-NNN)
├── progress.md # Date-based execution log (APPEND-ONLY!)
├── lessons.md # Anti-patterns, repeated mistakes, insights
├── experiments/ # EXP-NNN.md — ML experiments
├── plans/ # Detailed plans with DoD (done/ = completed)
├── notes/ # YYYY-MM-DD_HH-MM_topic.md — knowledge (5-15 lines)
└── reports/ # Reports and reviews
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.
- 2d ago Changed · -1 lines 3d330a7c2a3a
- 13d ago Changed · +2 lines 25265d700a22
- 22d ago Changed · +1 lines aaf8f239c78f
- 1mo ago Changed · +65 lines 14654bf2715d
- 1mo ago First seen · 463 lines · 46 tokens per session scan A 4fc93542d2fe
mb-manager is an agent published in the GitHub repository fockus/skill-memory-bank (28 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 5,521 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 2026-08-30.
Other agents, from other repositories
project-doc-ingestor
Ingests project documentation to extract context, conventions, and tech stack.
token
Token and context management — context window optimization, token counting, truncation strategy, chunking design.
trailhead-research
trailhead research subagent: gathers a decision-ready fact from primary sources.
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.
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.
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.