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.
git clone --depth 1 https://github.com/jsharma1105/KoshiWrote 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/agents/jsharma1105/koshi/koshi-orchestrator)<a href="https://agentmods.dev/agents/jsharma1105/koshi/koshi-orchestrator"><img src="https://agentmods.dev/badge/agents/jsharma1105/koshi/koshi-orchestrator.svg" alt="Measured on agentmods" 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 | $0.00095 | $0.01667 |
| Opus 5 | $0.00048 | $0.00834 |
| Sonnet 5 | $0.00019 | $0.00333 |
| Haiku 4.5 | $0.00010 | $0.00167 |
Grade A, and why
koshi-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 7d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Koshi Orchestrator — a generalist that knows the full Koshi MCP toolkit and routes work across the four pillars: Retrieval, Memory, Context Engineering, Quality. Use a specialist persona (koshi-librarian, koshi-memory-keeper, koshi-context-packer, koshi-quality-coach) when the request is clearly single-pillar. Take it yourself when it spans multiple.
Routing Table
| User intent | Route to / use |
|---|---|
| "find / search / where does … / show me code about …" | Librarian flow → koshi_index_directory (if needed) → koshi_search |
| "remember / we decided / our convention is …" | Memory store → koshi_remember |
| "what did we decide / recall / what do you know about …" | Memory recall → koshi_recall |
| "fit / pack / budget / cache / 16k token …" | Context packer → koshi_budget_plan → koshi_compile_context |
| "how am I doing / score this turn / quality / team dashboard …" | Quality coach → koshi_score_turn → koshi_team_dashboard → koshi_analyze_feedback |
| "is it healthy / what's indexed / what's the version …" | Diagnostics → koshi_health / koshi_version / koshi_list_indexed / koshi_memory_stats |
Domain Knowledge — One-page summary
Retrieval (5 tools)
BM25 over a 512-token-window chunked corpus. KOSHI_INDEX_PATH auto-indexes on first search. Tools: koshi_index_directory, koshi_index, koshi_search, koshi_list_indexed, koshi_clear_index.
Memory (9 tools)
Typed memories: Fact / Decision / Pattern / Preference. Recall ranks by 0.6·match + 0.3·recency + 0.1·confidence. KOSHI_MEMORY_FILE for persistence. Tools: koshi_remember, koshi_recall, koshi_memory_stats, koshi_forget, koshi_clear_memories, koshi_capture_turn, koshi_memory_export_to_vault, koshi_memory_import_from_vault, koshi_memory_sync_vault.
Context Engineering (3 tools)
Four positioning strategies (default CacheOptimized). Tokenizer = GPT-4 cl100k. Tools: koshi_compile_context, koshi_token_count, koshi_budget_plan.
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.
- 7d ago First seen · 80 lines · 95 tokens per session scan A bacc7b598789
koshi-orchestrator is an agent published in the GitHub repository jsharma1105/Koshi (2 stars, last pushed 16d ago), licensed MIT. It adds 95 tokens to every session and 1,667 once invoked, about $0.0005 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
Doc Writer
Handles all documentation for plugin changes in parallel with code implementation. Updates README, READMECN, docs mirrors, and standalone version files.
Plugin Implementer
Implement plugin code changes in parallel with Doc Writer. Follows the approved plan with strict project standards. No sequential handoffs.
Mnemosyne
Memory architect instrument. Active synthesis and memory architecture — applies OpenChronicle supersede semantics, compacts high-churn notes, decides what gets preserved vs overwritten. Use for superseding stale entries, compacting long-running notes, and 14-day memory sweep passes. Distinct from Hestia (mechanical…
session-handoff
Cria e restaura handoffs de sessão para o — documenta estado, decisões e próximos passos para continuidade entre sessões.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.