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 backend-workgit 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/backend-work)<a href="https://agentmods.dev/skills/pmikutel/directed-memory-bank/backend-work"><img src="https://agentmods.dev/badge/skills/pmikutel/directed-memory-bank/backend-work/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/backend-work"><img src="https://agentmods.dev/badge/skills/pmikutel/directed-memory-bank/backend-work.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 | $0.00025 | $0.00174 |
| Opus 5.5 | $0.00010 | $0.00070 |
| Sonnet 5.5 | $0.00005 | $0.00035 |
| Haiku 4.5 | $0.00003 | $0.00017 |
Grade A, and why
backend-work 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 1mo 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
backend-work
Routing skill for backend code work. Loads the memory-bank files relevant for backend changes.
Load:
memory-bank/project/brief.mdmemory-bank/technical/stack.mdmemory-bank/technical/backend.md(if present)memory-bank/technical/api-standards.md(if present)memory-bank/technical/quality.md(if present)
If a memory-bank/tasks/work/*.md file has branch: matching the current git branch, also load it.
No knowledge in this file — the listed files are the source. memory-bank/_index.md is the inventory if you need to discover what else exists.
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.
- 1mo ago First seen · 21 lines · 25 tokens per session scan A f20da55feb5e
backend-work is a skill published in the GitHub repository pmikutel/directed-memory-bank (6 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 174 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 2026-08-31.
Other skills, from other repositories
01-bootstrap
Design and validate a new SaaS's architecture into an INSTALL.md via Q&A and stack comparison. Use when the user starts a project, chooses a stack, or picks an architecture pattern. Not for editing an existing stack or scaffolding code.
api-contract-sync
Compare the selected API specification with actual route, handler, validation, and serialization contracts. Report verified drift, complete scoped agreement, or unverified coverage without changing code or specs.
audit-backend
Review backend SQL safety, error handling, API contracts, authorization, sensitive-data exposure and incomplete behavior with concrete source and caller evidence.
pagination-and-filtering
SocialApp pagination and filtering patterns — cursor-based SQL pagination, LIMIT+1 hasMore, TanStack infinite queries, admin table pagination, debounced search.
go-grpc-patterns
Upstream: https://pkg.go.dev/google.golang.org/grpc · https://grpc.io/docs/languages/go/.
nextjs-supabase-auth
Expert integration of Supabase Auth with Next.js App Router — server/client boundary, middleware for session refresh, Server Components, Server Actions, RLS. Use when the task mentions Supabase auth, Next.js auth, login, signup, OAuth, protected routes, or auth middleware.