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/commit)<a href="https://agentmods.dev/commands/fockus/skill-memory-bank/commit"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/commit/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/commit"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/commit.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 | $0.00029 | $0.00973 |
| Opus 5.5 | $0.00012 | $0.00389 |
| Sonnet 5.5 | $0.00006 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
commit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill bundle root
Every bundled helper below runs through the skill bundle root, never a bare scripts/… path (the
working directory is the user's project, where scripts/ is absent or belongs to someone else):
SKILL_DIR="${MB_SKILLS_ROOT:-${SKILL_DIR:-$HOME/.claude/skills/memory-bank}}"
[ -f "$SKILL_DIR/scripts/_lib.sh" ] || { echo "mb: skill bundle not found at $SKILL_DIR — set MB_SKILLS_ROOT" >&2; exit 2; }
0. Pre-flight safety checks
# Memory Bank drift — if the bank exists
[ -d .memory-bank ] && bash "$SKILL_DIR"/scripts/mb-drift.sh .
# Conflict markers / whitespace errors in what is about to be committed
git diff --check --cached
git diff --check
# Cross-session coordination board — if parallel sessions share this tree
[ -f .memory-bank/COORDINATION.md ] && bash "$SKILL_DIR"/scripts/mb-coord.sh active
If drift_warnings > 0, show the warnings to the user and ask whether to proceed. If git diff --check finds conflict markers or trailing-whitespace errors, stop and surface them — do not commit broken content.
If the coordination board exists, read its recent entries before committing: verify no FREEZE covers your files and the agreed commit ordering allows you to commit now; stage a scoped file list (never git add -A — the tree contains the other session's uncommitted diff), and append a COMMIT entry (hash + file scope) to the board after committing. Protocol: references/coordination.md.
1. Show staged changes
git status --short
git diff --cached --stat
git diff --cached
2. Scan the staged diff for forbidden patterns
Check for (in added lines only):
- Debug residue:
fmt.Println,console.log,debugger;,print((language-appropriate) TODO/FIXME/HACKmarkers in new code- Commented-out code blocks
- Hardcoded secrets (use the grep shape from
/security-review) - Files that should not be committed:
.env,*.pem,*.key,credentials.json
If any match appears, show the findings and ask whether to continue.
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.
- 9d ago Changed · +12 lines · +22 tokens per session 028d89c58b78
- 18d ago Changed · +10 lines 6bd1b982291a
- 1mo ago Changed 833fa2fc8f85
- 1mo ago First seen · 89 lines · 7 tokens per session scan A 909757cb1b1d
commit is a command published in the GitHub repository fockus/skill-memory-bank (26 stars, last pushed 8d ago), licensed MIT. It adds 29 tokens to every session and 973 once invoked, about $0.0001 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
checkpoint
Create a git commit checkpoint of current progress.
caveman-commit
Generate a terse caveman-style commit message for staged changes.
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits.
quick-commit
A quick Git command for committing and pushing a small code change. Git is the tool that records code versions and sends them to a shared repository.
git-workflow
Run review, tests, and commit steps, then prepare a pull request.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.