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 commands/solanabr/position-manager-skill/clmm-watchgit clone --depth 1 https://github.com/solanabr/position-manager-skillWrote 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/commands/solanabr/position-manager-skill/clmm-watch)<a href="https://agentmods.dev/commands/solanabr/position-manager-skill/clmm-watch"><img src="https://agentmods.dev/badge/commands/solanabr/position-manager-skill/clmm-watch.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 | $0.00015 | $0.00516 |
| Opus 5 | $0.00008 | $0.00258 |
| Sonnet 5 | $0.00003 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
clmm-watch 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 6d 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
/clmm-watch
Starts a reconnecting stream that fires an alert whenever a tracked position's current tick crosses its tickLower or tickUpper boundary.
Steps
-
Set environment variables (add to
.envor export in shell):# Primary: Yellowstone gRPC (preferred - lowest latency) export YELLOWSTONE_ENDPOINT="https://your-grpc-endpoint:10000" export YELLOWSTONE_TOKEN="your-token-here" # Fallback: Helius LaserStream websocket export HELIUS_API_KEY="your-helius-key" # Wallet to watch export OWNER_ADDRESS="YourWallet111..." -
Install dependencies (first run only):
npm install -
Run the watcher:
# tsx is in devDependencies; Node 22+/24 can also run TS natively: # node --experimental-strip-types skill/templates/watcher.ts npx tsx skill/templates/watcher.tsOr if compiled:
node dist/templates/watcher.js -
Expected output on startup:
[clmm-watch] Fetching positions for YourWallet111... [clmm-watch] Tracking 3 positions across orca, raydium, meteora [clmm-watch] Connected to Yellowstone gRPC -
Alert output when a position goes out of range:
[ALERT] OUT-OF-RANGE venue=orca pool=SOL/USDC tickCurrent=45210 tickLower=44000 tickUpper=45000 direction=above ts=2026-06-18T12:34:56.789Z -
Reconnect behavior: the watcher reconnects automatically on disconnect with exponential backoff (500ms base, 30s max). No manual restart needed.
-
Stop the watcher: press
Ctrl+C. The process exits cleanly; no transactions are ever submitted by this command.
Notes
- Positions are fetched once at startup; restart to pick up newly opened positions.
- For debugging stream issues, see
agents/stream-watcher.md. - This command is read-only and alert-only; it never signs or submits transactions.
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.
- 6d ago First seen · 71 lines · 15 tokens per session scan A 17106cea16c3
clmm-watch is a command published in the GitHub repository solanabr/position-manager-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 516 once invoked, about $0.0001 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 commands, from other repositories
deploy
Deploy Solana program (devnet first, then mainnet).
audit-strict
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Aggressively cuts false positives.
invariant
Generate Foundry invariant tests for property-based fuzzing. The high-value command for serious teams.
docs-remove
Remove a user-defined source alias from sources.yaml, optionally deleting its cached Markdown.
analyze
Conduct a full gas optimization analysis on a Foundry Solidity project.
checklist
Generate a custom checklist for the current feature based on user requirements.