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 skills add krakenfx/kraken-cli --skill kraken-error-recoverygit clone --depth 1 https://github.com/krakenfx/kraken-cliWrote 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/skills/krakenfx/kraken-cli/kraken-error-recovery)<a href="https://agentmods.dev/skills/krakenfx/kraken-cli/kraken-error-recovery"><img src="https://agentmods.dev/badge/skills/krakenfx/kraken-cli/kraken-error-recovery/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/krakenfx/kraken-cli/kraken-error-recovery"><img src="https://agentmods.dev/badge/skills/krakenfx/kraken-cli/kraken-error-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00018 | $0.01127 |
| Opus 5 | $0.00009 | $0.00563 |
| Sonnet 5 | $0.00004 | $0.00225 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
kraken-error-recovery 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 11d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kraken-error-recovery
Use this skill for:
- recovering from failed order submissions
- preventing duplicate orders after network errors
- handling partial fills and stuck states
- building resilient agent loops
Error Categories
Parse the .error field from the JSON response:
| Category | Meaning | Recovery |
|---|---|---|
auth |
Credentials invalid or expired | Re-authenticate, do not retry |
rate_limit |
Too many requests | Read suggestion and docs_url fields, adapt strategy |
network |
Connection failed | Retry with exponential backoff |
validation |
Invalid request parameters | Fix inputs, do not retry unchanged |
api |
Exchange-side rejection | Inspect error message, adjust request |
Duplicate Order Prevention
After a network error during order submission, the order may or may not have reached the exchange. Check before resubmitting:
kraken open-orders -o json 2>/dev/null
If the order appears in open-orders, do not resubmit. If absent:
kraken trades-history -o json 2>/dev/null
If the order filled immediately, it appears in trades. Only resubmit if the order is absent from both.
Client Order ID for Idempotency
Use --cl-ord-id to tag orders with a unique identifier:
kraken order buy BTCUSD 0.001 --type limit --price 50000 --cl-ord-id "dca-2024-01-15-001" -o json 2>/dev/null
If the submission fails, query by client order ID to check if it reached the exchange:
kraken open-orders --cl-ord-id "dca-2024-01-15-001" -o json 2>/dev/null
Cancel by client order ID if needed:
kraken order cancel --cl-ord-id "dca-2024-01-15-001" -o json 2>/dev/null
Network Error Recovery Pattern
1. Submit order (capture exit code and response)
2. If exit code != 0 and error == "network":
a. Wait 2 seconds
b. Check open-orders for the order (by cl-ord-id or recent orders)
c. If found → order succeeded, proceed
d. If not found → check trades-history
e. If in trades → order filled, proceed
f. If absent from both → safe to retry
3. Retry with same cl-ord-id
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.
- 11d ago First seen · 137 lines · 18 tokens per session scan A bf40ed09d015
kraken-error-recovery is a skill published in the GitHub repository krakenfx/kraken-cli (715 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,127 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 2026-08-30.
Other skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
bridge
Cross-chain token transfers using Wormhole and CCTP.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.