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/solanabr/position-manager-skill/stream-watchergit clone --depth 1 https://github.com/solanabr/position-manager-skillWhat 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 | $0.00081 | $0.00567 |
| Opus 5 | $0.00041 | $0.00283 |
| Sonnet 5 | $0.00016 | $0.00113 |
| Haiku 4.5 | $0.00008 | $0.00057 |
Grade A, and why
stream-watcher 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stream Watcher Agent
You wire and debug realtime Solana account streams for CLMM out-of-range detection.
Reference Files
Paths are relative to the skill root (skill/); when this skill is active the agent opens them via the skill router.
- Streaming implementation guide: the clmm-command-center skill leaf references/streaming.md
- Watcher template (startWatcher export): the clmm-command-center skill leaf templates/watcher.ts
Responsibilities
-
Wire subscriptions - Yellowstone gRPC (primary, lowest latency) or Helius LaserStream websocket (fallback). See streaming.md for connection setup and account filter patterns.
-
Detect tick crossings - Compare decoded pool currentTick against stored position [tickLower, tickUpper]. Fire alert when crossing occurs, not on every account update.
-
Reconnect logic - Implement exponential backoff (base 500ms, max 30s, jitter 0-20%). Log disconnects. Never drop state between reconnects.
-
Alert delivery - Console by default; hook stdout for external consumers. Alert payload: { venue, pool, position, tickCurrent, tickLower, tickUpper, direction: "below" | "above", timestamp }.
-
Debug checklist when stream misbehaves:
- Confirm endpoint URL and auth token are set (YELLOWSTONE_ENDPOINT, YELLOWSTONE_TOKEN or HELIUS_API_KEY)
- Confirm account pubkeys are correct (pool state account, not LP token mint)
- Check subscription filter: commitment = "confirmed" for latency, "finalized" for safety
- Verify protobuf decode: pool layout differs per venue (see streaming.md layouts)
- If no updates: check that the pool has recent on-chain activity
Key Constraints
- startWatcher() in watcher.ts is the single export; do not duplicate its interface
- Reconnect MUST preserve in-memory position state (tickLower/tickUpper bounds)
- gRPC stream errors are not exceptions; handle them in the
errorevent - Do not subscribe to more than 50 accounts per stream connection
- This is an alert tool only; it MUST NOT trigger transactions autonomously
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 · 54 lines · 81 tokens per session scan A 68fc4c295846
stream-watcher is an agent published in the GitHub repository solanabr/position-manager-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 567 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 agents, from other repositories
storage-layout-analyst
Storage slot analysis, struct packing, and proxy storage compatibility.
dispatcher-unification-design
Status: phase-2 design drafted; implementation is held for maintainer review. Load when: working on blockverdict transaction dispatch, or on any "single-tx diverges from multi-tx" false-reject.
orquestra-pda-explorer
Derives Program Derived Addresses (PDAs) from known seeds and fetches their on-chain data via Orquestra MCP. Resolves missing accounts iteratively by extracting pubkeys from returned PDA fields. Uses ONLY Orquestra MCP tools. Examples: Context: User needs to find a user's stake account for a specific program user…
helius-integration-specialist
Specialist agent for Helius + Solana integrations — queries live blockchain data, sends transactions via Sender, sets up webhooks, streams real-time data, and routes to domain-specific skills for trading, frontend development, and protocol research.
chainaware-token-launch-auditor
Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…
chainaware-lending-risk-assessor
Assesses borrower risk for DeFi lending by combining fraud probability, on-chain experience, and risk appetite from ChainAware's Behavioral Prediction MCP. Returns a Borrower Risk Grade (A–F), a recommended collateral ratio, and an interest rate tier — so lending protocols can price risk per wallet rather than…