Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/fockus/skill-memory-banknpx agentmods add commands/fockus/skill-memory-bank/workWrote 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/commands/fockus/skill-memory-bank/work)<a href="https://agentmods.dev/commands/fockus/skill-memory-bank/work"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/work.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.10839 |
| Opus 5 | $0.00014 | $0.05420 |
| Sonnet 5 | $0.00006 | $0.02168 |
| Haiku 4.5 | $0.00003 | $0.01084 |
Grade A, and why
work 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 — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mb work [target] [--workflow NAME] [--review] [--fix] [--loop N] [--range A-B] [--auto] [--dry-run] [--budget TOK] [--max-cycles N] [--allow-protected]
Run the executable engine using a workflow mode resolved from pipeline.yaml. By default, /mb work is intentionally simple: implement → verify → done from an already-created plan/spec. Projects can opt into stricter local modes such as governed-execution (implement → verify → review ensemble → judge → fix/backlog → done), full-cycle (discuss → sdd → plan → implement → verify → done), requirements-plan, implement-only, review-fix, or review-only. Severity gates, judge gates, token budgets, protected-path checks, and the sprint context guard provide hard stops for --auto mode.
Scope. Phase 3 Sprint 1 shipped
pipeline.yaml. Sprint 2 shipped target resolution, range parsing, role-detection, plan emission, implement-step dispatch — and extended execution to spec tasks (specs/<topic>/tasks.md) as a first-class source alongside plan stages. Sprint 3 (this command) wires the review-loop, severity gates, fix-cycle, plan-verifier integration,--autohard stops,--budgettoken tracking, and protected-path enforcement.Phase 4 will add:
--slim/--fullcontext strategy viacontext-slim-pre-agent.shandpre-agent-protected-paths.shruntime hooks;superpowers:requesting-code-reviewskill auto-detection in the installer.
Why /mb work?
Plans declared with /mb plan carry stage markers, DoD, and TDD instructions. Specs created with /mb sdd carry <!-- mb-task:N --> markers in specs/<topic>/tasks.md, each linked to REQ-IDs. /mb work consumes both for execution modes: pick a work item (stage or task), route it to the right role-agent (mb-backend, mb-frontend, mb-ios, mb-android, mb-architect, mb-devops, mb-qa, mb-analyst, with mb-developer as fallback), let the agent implement against the DoD, verify the result, then put the verified diff through a real reviewer-approval loop instead of trusting the implementer's self-assessment. For full-cycle modes, /mb work first delegates to the same contracts as /mb discuss, /mb sdd, and /mb plan before executing work items.
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 · 401 lines · 28 tokens per session scan A 81d6ce54b7ef
work is a command published in the GitHub repository fockus/skill-memory-bank (24 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 10,839 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 2026-09-03.
Other commands, from other repositories
dashboard
Show the repo dashboard: the pinned index of every open map, the whiteboard, and live counts.
pause
Checkpoint the ticket in play so it can be resumed later.
resume
Resume a paused ticket from its checkpoint.
whiteboard
Show the whiteboard: loose (map-less) tickets, their frontier and who holds each.
work
Work the next frontier ticket, or the one you name.
bug
Capture a bug ticket (use --of for a regression).