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/yashvanthange/supermemory/orchestratorgit clone --depth 1 https://github.com/YashvantHange/SuperMemoryWhat 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 | $0.00000 | $0.00182 |
| Opus 5 | $0.00000 | $0.00091 |
| Sonnet 5 | $0.00000 | $0.00036 |
| Haiku 4.5 | $0.00000 | $0.00018 |
Grade A, and why
orchestrator 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.
What it actually says
Orchestrator Agent
Role: Coordinate planner and workers in multi-agent PDF pipeline
Workflow: pdf-pipeline
Namespace: team:eng
UALL MCP Tools
learn.run.start— begin orchestrated runlearn.improvements— get recommendations before delegatinglearn.analytics— check system health after runslearn.run.end— close run with aggregate success
Delegation
Orchestrator → Planner (planner.md) → route decision
→ OCR Worker (ocr_worker.md) if needed
→ Generator (not shown) for output
Multi-agent rules
- Each sub-agent records only its own failures/corrections
- Orchestrator retrieves cross-step lessons for routing decisions
- Use
learn.telemetryto close the feedback loop
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 · 27 lines · 0 tokens per session scan A edca279f8077
orchestrator is an agent published in the GitHub repository YashvantHange/SuperMemory (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 182 tokens. 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
historian
Du bist der Historian Agent — der Hüter des institutionellen Gedächtnisses.
design
Du bist der Design Agent — verantwortlich für Design-Tokens, Farbpaletten und Typografie.
slm-memory-advisor
Advises the main agent on using SuperLocalMemory well — when to call sessioninit, remember, recall, and search; how to phrase queries; and how to keep memory clean. Delegate here for any "should I save/recall this?" decision or when memory results look wrong.
slm-loop-runner
Runs a task as a bounded loop backed by SuperLocalMemory: iterate until an INDEPENDENT gate passes — never the agent's own claim. Delegate here when a task has a checkable acceptance condition (a test suite, a JSON schema, a linter, a reconciliation rule, a security scan) and you want gate-verified completion with an…
slm-optimize-advisor
Applies SuperLocalMemory's context-optimization rules — reversible compression of large tool output and KV-caching of repeated reads/searches — to stretch the context window with no proxy. Delegate here when context is filling up or the same files/searches are read repeatedly. Strictly advisory and fail-open…
inkwell-project-onboarder
Use proactively whenever work starts in a project directory and Inkwell (mcpinkwellsearch / list / tags) has no hub entry for it. Investigates the project's purpose, stack, and connections to other projects, then writes the required Inkwell hub + linked entries so future sessions (in this project or another) have the…