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 skills/lorismascio17/droste-memory/droste-code-memorynpx skills add lorismascio17/droste-memory --skill droste-code-memorygit clone --depth 1 https://github.com/lorismascio17/droste-memoryWhat 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 | $0.00075 | $0.00599 |
| Opus 5 | $0.00037 | $0.00300 |
| Sonnet 5 | $0.00015 | $0.00120 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
droste-code-memory 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 2d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Droste Code Memory
Use Droste as Claude's local structural + semantic memory layer for codebases. Prefer it before broad file reads when the task needs repository context, symbol relationships, caller/callee edges, or MCP-backed retrieval.
Core Workflow
- Confirm Droste is installed:
droste --version
If uncertain, run scripts/check_droste.py from this skill.
- Use an isolated DB for serious multi-repo work. Put
--dbbefore the command:
droste --db /absolute/path/to/droste_memory_db.json status
droste --db /absolute/path/to/droste_memory_db.json index . --reset
- Index the current repo before asking for context:
droste index .
Use --reset only when the selected DB belongs to the current repository.
- Retrieve focused context:
droste context "authentication flow" --budget 3000 --json
Use Droste output to choose exact files and symbols to inspect. Do not make final claims from retrieved context alone; verify relevant source files.
- Use MCP for persistent Claude workflows:
droste mcp
Read references/claude-mcp-config.md when configuring Claude Desktop,
Claude Code, or another Claude-facing MCP client.
Safety Rules
- Do not reset a shared/global Droste DB unless the user explicitly asked.
- Do not index secrets, dependency caches, build output,
.droste/, or private generated graph JSON. - If Droste reports multi-root warnings, pass an explicit DB or root instead of accepting mixed context.
- Prefer source paths under the current repository. Treat unrelated absolute paths as suspicious until verified.
- Redact any secret-like value before reporting it.
Useful Commands
droste status --json
droste context "query" --budget 1500
droste context "query" --budget 3000 --json
droste zoom "symbolName" --no-open
droste view
Expected MCP Tools
When the Droste MCP server is connected, use:
droste_index_projectto index the current repository.droste_get_contextto retrieve causal context for a query.droste_statusto inspect storage, active root, symbols and warnings.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 87 lines · 75 tokens per session scan A d59927352b1b
droste-code-memory is a skill published in the GitHub repository lorismascio17/droste-memory (3 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 599 once invoked, about $0.0004 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
Sverklo Code Intelligence
Gives you deep codebase understanding — semantic search, blast-radius analysis, PR review, and health audits.
memtrace-first
Route code discovery, debugging, flow tracing, how-code-works questions, and pre-edit rationale checks in indexed source-code repos to Memtrace graph plus Cortex decision tools. Use first before searching/reading code, and before editing, refactoring, deleting, or re-picking an approach that may have a recorded…
memtrace-style-fingerprint
Pull the codebase's empirical style norm from Memtrace and match it when writing or editing source code in an indexed repo. Use when choosing between competing idioms (ternary vs if-else, arrow vs function declaration, const vs let, await vs .then, early-return vs nested-return), matching naming case, or when the user…
memtrace-decision-memory
Use Cortex decision memory through the normal Memtrace MCP tools. Trigger for free-text questions about what was decided, chosen, rejected, banned, or established as a convention; for why a symbol exists or which contracts constrain it; for whether a known decision held, drifted, or was violated; and for the…
memtrace-docs
Use official hosted Memtrace documentation before guessing, web search, or stale local copies. Trigger when the user asks how Memtrace works; how to install, configure, or deploy CLI, MCP, fleet, Cortex, or enterprise MemDB; what tools, skills, or commands exist; wants to find or locate official docs for a topic; or…
memtrace-evolution
Trace source-code change history from Memtrace's symbol-level temporal memory. Use when the user asks about change history, recent modifications, what changed since a date, symbol timeline, evolution, unexpected changes, or incident timelines. Do not use git log, git diff, Grep, or manual file search to reconstruct…