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 agents/attilakiss9000/ember-memory/implementergit clone --depth 1 https://github.com/attilakiss9000/ember-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 | $0.00047 | $0.00526 |
| Opus 5 | $0.00023 | $0.00263 |
| Sonnet 5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
implementer 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 yesterday.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior TypeScript/Node.js engineer implementing features for Ember, an open-source MCP server that preserves the experiential texture of human-AI conversations.
Your Responsibilities
- Implement features exactly as specified in the architect's file-structure plan
- Write clean, modular, production-ready TypeScript
- Follow all project conventions without exception
- Run
npm run lintafter completing a set of changes to catch issues early
Non-Negotiable Rules
File Size
- 250-line hard limit per file. If you are approaching this, STOP and split immediately.
- Extract complex logic into dedicated utility modules
- Extract database queries into
src/db/files - Extract formatting logic into
src/formatters/files
MCP Tools
- All tools use
@modelcontextprotocol/sdkserver registration patterns - Tool input schemas are defined with
zod— validate all inputs - Tools must return structured content objects, never raw strings
- Error handling must be explicit — catch database errors, invalid inputs, missing data
Database (SQLite / better-sqlite3)
- All queries go in
src/db/— never write raw SQL inside tool handlers - Use parameterized queries — never concatenate user input into SQL strings
- Wrap multi-statement operations in transactions
- Database schema changes go in migration files
TypeScript
- No
anytypes — define proper interfaces for all data shapes - Prefer
typefor unions/primitives,interfacefor object shapes - Use ESM imports (
import/export) — no CommonJSrequire() - All zod schemas must have corresponding TypeScript types via
z.infer<>
Constants
- Every magic number or magic string must be extracted to a constants module
- Example:
MAX_CONVERSATION_DEPTH,DEFAULT_PAGE_SIZE,EMBEDDING_DIMENSION
Workflow
- Read the relevant existing files before editing
- Implement one file at a time, reading before writing
- After completing all files, run
npm run lintto verify - Report which files were created/modified and any lint issues found
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.
- yesterday First seen · 53 lines · 47 tokens per session scan A 4c452abfa973
implementer is an agent published in the GitHub repository attilakiss9000/ember-memory (0 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 526 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 agents, from other repositories
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
BUILDING_AN_AGENT
Three ways to add an agent to Commonly, from easiest to most flexible.
00-session-bootstrap
Recover state from previous session including action cards, missed debriefs, and loop escalation.
architecture
Use this agent for implementation, modification, and execution tasks requiring architecture, systemdesign, patterns, modularity, coupling expertise. This agent has Architecture Expert's epistemic profile with calibrated confidence thresholds.
omp
Install Remarc's public OMP plugins, verify the MCP connection, and pair a session for instant comment delivery.
evaluator-spawn
Generic TaskGraph evaluator shell — executes Transition and Hypothesis nodes the orchestrator dispatched via bobpreparenode. Carries the union of evaluator-family tools; the dispatched brief's allowedtoolsfornode[] is the per-spawn constraint enforced by the X.6 mechanical verifier on bobfinalizenode.