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.
npx agentmods add commands/fockus/skill-memory-bank/plangit clone --depth 1 https://github.com/fockus/skill-memory-bankWhat 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 | $0.00014 | $0.02142 |
| Opus 5 | $0.00007 | $0.01071 |
| Sonnet 5 | $0.00003 | $0.00428 |
| Haiku 4.5 | $0.00001 | $0.00214 |
Grade A, and why
plan 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan: $ARGUMENTS
Canonical planning command. /mb plan is an alias that dispatches here.
Storage note. Resolve the active bank path through
mb_resolve_path(inscripts/_lib.sh). The plan file ends up at<resolved-bank>/plans/<YYYY-MM-DD>_<type>_<topic>.mdregardless of whether the bank is local, registered global storage, or legacy.claude-workspace. If[MEMORY BANK: ABSENT](rules-only mode), refuse to plan and tell the user to run/mb initfirst — but do not auto-initialize.
0. Validate arguments
Parse $ARGUMENTS into <type> <topic>. Allowed type: feature, fix, refactor, experiment. If type is missing or not in the allowed set, stop and ask the user. If topic is empty, stop and ask.
Hierarchy reminder: Phase → Sprint → Stage. See
references/templates.md§ Plan decomposition for sizing rules. Cyrillic «Этап / Спринт / Фаза» — legacy alias; the scaffold script will soft-warn if you use them in<topic>.
1. Preparation
Read before you start:
~/.claude/CLAUDE.md— global rules~/.claude/skills/memory-bank/references/templates.md— MUST read the "Plan decomposition — Phase → Sprint → Stage" section./RULES.MD(project-level, if present) — project-specific decomposition rules + 200k-per-Sprint hard limit./.memory-bank/roadmap.md— current priorities (if present)./.memory-bank/checklist.md— current tasks (if present)./.memory-bank/lessons.md— known anti-patterns (if present)./.memory-bank/codebase/*.md— stack / architecture / conventions / concerns summaries (if populated)
Study the codebase in the context of the topic. Find and read the files relevant to "$ARGUMENTS".
1.5. Decompose by size — Phase / Sprint / Stage
Before scaffolding, estimate the scope:
| Estimate | Target structure | Plan file(s) |
|---|---|---|
| ≤ 3 stages, one session | Plain plan (no Phase/Sprint) | 1 file, 3-5 <!-- mb-stage:N --> markers |
| 3-7 stages, several days | One Sprint = one plan file | 1 file, 5-7 stages |
| ≥ 2 Sprints with dependencies | Phase roadmap + one plan file per Sprint | 1 roadmap + N Sprint plan files |
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 First seen · 168 lines · 14 tokens per session scan A e7fd86de0b47
plan is a command published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 2,142 once invoked, about $0.0001 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.
Other commands, from other repositories
story-implement
Implement a story through the Implement Phase. Stories must be fully designed with chunks before implementation.
planning
Feature roadmap and planning. Manage initiatives, concepts, open questions, and story creation from planning.
story-new
Create a new story. It lands in the backlog until assigned to a cycle.
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.
cycle-complete
Complete a cycle. Triggers reflection if pending learnings, then archives.
cycle-design
Design a cycle — create new cycles with planned stories, detail existing planning cycles, or quick-sketch a roadmap. Detects planning docs in .craft/planning/ and sources the cycle from them when relevant.