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 skills add pmikutel/directed-memory-bank --skill memory-bank-writergit clone --depth 1 https://github.com/pmikutel/directed-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/skills/pmikutel/directed-memory-bank/memory-bank-writer)<a href="https://agentmods.dev/skills/pmikutel/directed-memory-bank/memory-bank-writer"><img src="https://agentmods.dev/badge/skills/pmikutel/directed-memory-bank/memory-bank-writer/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/skills/pmikutel/directed-memory-bank/memory-bank-writer"><img src="https://agentmods.dev/badge/skills/pmikutel/directed-memory-bank/memory-bank-writer.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 | $0.00032 | $0.00431 |
| Opus 5 | $0.00016 | $0.00216 |
| Sonnet 5 | $0.00006 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
memory-bank-writer 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
memory-bank-writer
Routing skill for writes to memory-bank/. Loads the inventory and the RAM-layer process so the agent knows what exists and how to maintain it.
Load:
memory-bank/project/doc-guide.md— required. Style, length, and hygiene rules for every memory-bank file.memory-bank/_index.md(the inventory — needed when authoring writes)memory-bank/tasks/process.mddocs/what-goes-where.md(if this project ships the standard's docs alongside)
Rules of thumb:
- Follow
doc-guide.mdon every write. Length budgets, no duplication, bullets over paragraphs, reference don't copy. - Decision rationale lives in two places: inline
**Why:**intechnical/<topic>.md(standing rule) and chronologically intasks/log/pr-*.md(the moment). If a log entry's rationale recurs or becomes a coding rule, followtasks/process.md→ promote durable knowledge totechnical/. Don't create adecisions/directory. - Knowledge layer files (
project/,technical/) change slowly. Update only when the underlying truth has shifted. - When you add or rename a memory-bank file, update
_index.mdfirst, then update any integration-layer artefact (skill, rule, hook,AGENTS.md) that should reference the new file. tasks/work/<slug>.md: update frontmatter (status,branch,updated) as state changes. Don't fabricate scratchpads that won't be useful.tasks/log/pr-<num>-<slug>.md: typically written by automation on PR merge. Scale length to complexity (3–6 / 8–12 / 15–20 lines). Don't document routine quality checks as achievements.
No knowledge in this file — see the listed files.
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 First seen · 27 lines · 32 tokens per session scan A 0cf5596d33f0
memory-bank-writer is a skill published in the GitHub repository pmikutel/directed-memory-bank (5 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 431 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
02-project-memory
Build the project's memory of its architecture, conventions, and decisions, and wire it into your AI tools. Use when the user wants to set up or refresh project memory, or rewire it into a tool. Not for editing one existing memory file.
10-learn
Capture durable project learnings. Use when the user wants to remember, record, or formalize a decision, convention, lesson, pitfall, reusable workflow, or review finding. Not for preferences or temporary notes.
powercontext-project-context
Use PowerContext to search prior project decisions, explicitly save or correct durable memory, inspect scopes and review candidates, or transfer and resume work with exact evidence. Use when the user requests these operations or relevant project history is missing; ordinary coding and current-turn summaries do not…
project-context
Use PowerContext project memory and handoff tools through MCP when continuing prior work, recalling decisions, maintaining durable memory, or transferring work across tasks, sessions, or agents.
powercontext
Use PowerContext for durable memory, cross-session continuity, and reviewed Experience or Skill artifacts.
contorium-workspace-memory
Use Contorium workspace memory layers (focus, session events, Git, export) when resuming AI work or avoiding repeated project explanation.