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/commands/fockus/skill-memory-bank/catchup)<a href="https://agentmods.dev/commands/fockus/skill-memory-bank/catchup"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/catchup/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/catchup"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/catchup.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 | $0.00040 | $0.00343 |
| Opus 5.5 | $0.00016 | $0.00137 |
| Sonnet 5.5 | $0.00008 | $0.00069 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
catchup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Skill bundle root
Every bundled helper below runs through the skill bundle root, never a bare scripts/… path (the
working directory is the user's project, where scripts/ is absent or belongs to someone else):
SKILL_DIR="${MB_SKILLS_ROOT:-${SKILL_DIR:-$HOME/.claude/skills/memory-bank}}"
[ -f "$SKILL_DIR/scripts/_lib.sh" ] || { echo "mb: skill bundle not found at $SKILL_DIR — set MB_SKILLS_ROOT" >&2; exit 2; }
Steps
- Read
~/.claude/CLAUDE.md - If
./.memory-bank/exists:- Read
status.md,checklist.md,roadmap.md, and the latest note fromnotes/ - If
.memory-bank/codebase/*.mdis populated, include a one-line summary per doc (viabash "$SKILL_DIR"/scripts/mb-context.shorhead -3on each file)
- Read
- Run
git diffandgit diff --staged— show what is currently in progress - Run
git log --oneline -5— show the latest commits - Summarize in 3-5 sentences: what is done, what is in progress, and what comes next
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.
- 11d ago Changed · +30 tokens per session 5f0fc7479c5a
- 20d ago Changed · +12 lines 1fcf5a3ea19a
- 1mo ago First seen · 12 lines · 10 tokens per session scan A 7cebb8db711d
catchup is a command published in the GitHub repository fockus/skill-memory-bank (26 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 343 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 commands, from other repositories
tree
Show the Tau Git Memory tree as a visual schema.
sync
Sync memory between your local machine and GitHub backup — both directions.
status
Run Tau Git Memory status now.
sync-from-github
Sync one vault or the whole fleet straight from the GitHub skeleton (plugins, themes, snippets, root docs) — no dev repo or local .template needed. Same guards as --sync-plugins (credential-leak refusal, BRAT anti-downgrade) plus hardened archive extraction. (Skill sync-from-github carries the full procedure.).
full-check
Run a thorough scan of the entire memory ecosystem. Recommended weekly or after major changes.
backup
Push local memory files to your GitHub backup repository.