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/teamWrote 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/team)<a href="https://agentmods.dev/commands/fockus/skill-memory-bank/team"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/team/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/commands/fockus/skill-memory-bank/team"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/team.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 | $0.00041 | $0.04930 |
| Opus 5.5 | $0.00016 | $0.01972 |
| Sonnet 5.5 | $0.00008 | $0.00986 |
| Haiku 4.5 | $0.00004 | $0.00493 |
Grade A, and why
team 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 today.
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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mb team: $ARGUMENTS
Run one task as several tracks in parallel, all editing one integration tree. Tracks are role agents
(mb-backend, mb-frontend, …); each owns a set of file globs, writes one report and talks only to the board.
You are the orchestrator and the runtime. scripts/mb-team.sh is a stateless brain plus the single writer of
<bank>/reports/<topic>/team.json: next prints actions and changes nothing; you execute them with host tools and
record the result with track set. Everything is resumable after compaction from team.json, the brief, the reports
and the board. There is no daemon and no push path.
Run every command from the project root (or pass --mb <bank>): mb-team.sh refuses a working directory inside
a Memory Bank, so no nested bank appears.
0. Setup
SKILL_DIR="${SKILL_DIR:-$HOME/.claude/skills/memory-bank}" # skill bundle root
# shellcheck source=../scripts/_lib.sh
. "$SKILL_DIR/scripts/_lib.sh"
BANK="$(mb_resolve_path "${BANK:-}")"
team() { bash "$SKILL_DIR/scripts/mb-team.sh" --mb "$BANK" "$@"; }
With one open team in the bank, --topic is optional; with several, add --topic <topic> anywhere on the line.
1. Start a team — init
# --no-goal only when the user agrees there is no goal.md; otherwise --goal G-NNN (goal.md must validate)
team init "$TOPIC" --no-goal --tree "$PWD" --max-parallel 4
init refuses a second team with the same topic, records the VCS kind, root and HEAD of --tree (the baseline),
renders reports/<topic>/brief.md and posts FREEZE · contract:<topic> on the board. Attributes:
| Attribute | Meaning |
|---|---|
--goal G-NNN · --no-goal |
Goal whose acceptance gates stop_success (mb-goal-validate.sh must pass) · no goal |
--plan P |
Plan or spec the team implements; bank-relative or absolute |
--tree DIR · --mirror DIR |
Integration tree (default: cwd) · read-only mirror for external reviewers |
--max-parallel N |
Active tracks at once (default team.max_parallel) |
--budget TOK |
Token budget under run id team-<topic>; add per-track spend with mb-work-budget.sh add <tokens> --run-id team-<topic> |
--team-review |
Turn on team review cycles for this run (§8) |
--title T · --host H |
Display title · host whose model profile maps premium/mid (default claude-code) |
| pipeline attributes | Team layer for every track (§2) |
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.
- today First seen · 269 lines · 41 tokens per session scan A 51e2415f3173
team is a command published in the GitHub repository fockus/skill-memory-bank (26 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 4,930 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 2026-10-19.
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.
prune
Prune a map's closed and orphan sub-issue edges to reclaim slots under GitHub's 100-cap (references kept).