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/profilegit 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 | $0.00018 | $0.01271 |
| Opus 5 | $0.00009 | $0.00635 |
| Sonnet 5 | $0.00004 | $0.00254 |
| Haiku 4.5 | $0.00002 | $0.00127 |
Grade A, and why
profile 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 3d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/profile — Rule profiles & stack presets
The /profile command manages Memory Bank rule profiles: configurable per-role, per-stack, per-architecture, and per-delivery-method rules that sit on top of the immutable safety baseline.
Underlying script: scripts/mb-profile.sh.
Purpose
Memory Bank rules have two layers:
- Immutable safety baseline — always active, cannot be disabled by any profile, task instruction, or user choice (see below).
- Configurable preferences — role, stack, architecture, delivery presets that personalize guidance without weakening safety.
/profile controls the configurable layer. It reads from and writes to:
- User-global profile:
<agent-config>/memory-bank/rules-profile.json(e.g.~/.claude/memory-bank/rules-profile.json). No project files are written — works even when[MEMORY BANK: ABSENT]. - Project profile:
<resolved-mb>/rules-profile.json(requires an active Memory Bank).
Subcommands
| Subcommand | One-liner |
|---|---|
init |
Create a new profile interactively or via flags |
show |
Print the resolved merged profile (all layers) |
path |
Print the active profile path and which layer it came from |
validate |
Validate a profile file — exits 0 if valid, 1 with errors otherwise |
set |
Update a single field in user or project profile |
Usage examples
# Create a user-global backend/Go profile (no project Memory Bank needed):
mb-profile.sh init --scope=user --role=backend --stack=go \
--architecture=microservices --delivery=contract-first
# Create a project-scoped frontend/TypeScript profile:
mb-profile.sh init --scope=project --role=frontend --stack=typescript \
--architecture=fsd --delivery=sdd
# Create a mobile/generic profile:
mb-profile.sh init --scope=user --role=mobile --stack=generic \
--architecture=mobile-udf --delivery=api-first
# Create a Python data service profile:
mb-profile.sh init --scope=project --role=backend --stack=python \
--architecture=modular-monolith --delivery=tdd
# Create a Java DDD profile:
mb-profile.sh init --scope=project --role=backend --stack=java \
--architecture=ddd --delivery=api-first
# Show the resolved profile (user + project merged):
mb-profile.sh show
# Show where the active profile file lives:
mb-profile.sh path
# Validate an existing profile:
mb-profile.sh validate .memory-bank/rules-profile.json
# Update a single field (project scope):
mb-profile.sh set --scope=project --strictness=block
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.
- 3d ago First seen · 145 lines · 18 tokens per session scan A d9d871a44bc6
profile is a command published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,271 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
todo
The quality-gated task list: tasks with real descriptions, testable acceptance criteria, and evidence — a task only closes when the controller agrees it is done.
release
The pre-tag controller: version sync, changelog, clean tree, gate, and suite — every failure listed, the tag printed, never run.
security
The security pass: secrets (blocking), SAST, dependency vulns — plus the index's entry points to review from.
init
Install the formatters this repository needs, with every command visible before it runs.
vitaecontext-github
Audit or improve GitHub profile and repository SEO.
test
Run the test suite for the given package and summarize failures.