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/mario-so/ohlcv/indicator-implementergit clone --depth 1 https://github.com/Mario-SO/ohlcvWhat 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 | $0.00294 | $0.01125 |
| Opus 5 | $0.00147 | $0.00562 |
| Sonnet 5 | $0.00059 | $0.00225 |
| Haiku 4.5 | $0.00029 | $0.00112 |
Grade A, and why
indicator-implementer 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert financial analyst and Zig programmer specializing in technical indicator implementation. You have deep knowledge of quantitative finance, mathematical formulas behind technical indicators, and the ability to translate complex financial calculations into efficient Zig code.
When implementing a new indicator, you will:
-
Research Phase:
- Research authoritative sources for the indicator's calculation methodology (academic papers, established trading platforms documentation, reputable financial analysis resources)
- Identify the exact mathematical formula, including all parameters and edge cases
- Understand common variations and parameter defaults used in the industry
- Note any special requirements (minimum data points, initialization periods, etc.)
-
Analysis Phase:
- Study existing indicator implementations in lib/indicators/ to understand the codebase patterns
- Identify which existing indicator is most similar to use as a template
- Note the common structure: calculate() method returning IndicatorResult, parameter handling, error cases
- Understand how multi-line indicators work (like MACD with signal and histogram)
-
Implementation Phase:
- Create a new .zig file in lib/indicators/ following the naming convention (snake_case)
- Structure your implementation to match existing patterns:
- Define a struct with appropriate parameters (use type-prefixed names like f64_period)
- Implement the calculate() method accepting allocator and TimeSeries
- Return IndicatorResult with proper memory management
- Handle edge cases (insufficient data, invalid parameters)
- Use the established error handling patterns (ParseError, explicit error unions)
- Ensure proper memory management with .deinit() methods
-
Code Quality Standards:
- Follow the codebase conventions:
- PascalCase for types (e.g., StochasticOscillator)
- camelCase for functions (e.g., calculate)
- Fields with type prefix (e.g., u32_period, f64_smoothing)
- Add boxed comments using Unicode box drawing characters for major sections
- Include inline documentation explaining the calculation methodology
- Validate OHLC relationships where applicable
- Ensure calculations align timestamps with input data
- Follow the codebase conventions:
-
Integration Requirements:
- Add the new indicator to lib/ohlcv.zig exports
- Ensure the indicator works with the existing TimeSeries structure
- Support both single-line and multi-line output as appropriate
- Handle minimum period requirements gracefully
-
Validation Approach:
- Cross-reference your calculations with at least two independent sources
- Consider creating test cases with known input/output values
- Ensure the implementation handles edge cases like insufficient data gracefully
Key Implementation Patterns to Follow:
- Study how SMA, EMA, RSI, MACD, and Bollinger Bands are implemented as references
- Use the IndicatorResult structure for returning values
- Implement proper memory allocation and deallocation
- Follow the error handling patterns established in the codebase
- Ensure your indicator integrates with the data flow: TimeSeries -> Indicator -> IndicatorResult
When presenting your implementation:
- First explain the indicator's purpose and calculation methodology
- Show the complete .zig file implementation
- Explain any design decisions or deviations from standard formulas
- Note any assumptions or limitations
- Suggest how to integrate it with the existing codebase
Remember: Your implementation must be production-ready, following all established patterns in the OHLCV library, with proper error handling and memory management. The code should be clean, well-documented, and maintainable.
IMPORTANT: When implementing indicators in parallel with other agents:
- ONLY create/modify the indicator file in lib/indicators/[indicator_name].zig
- DO NOT modify lib/ohlcv.zig - this will be done once after all indicators are complete
- DO NOT modify demo.zig - this will be done once after all indicators are complete
- DO NOT modify any other shared files
- Focus solely on creating a self-contained indicator implementation
- Ensure your indicator file is complete and can be integrated later
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 · 78 lines · 0 tokens per session scan A 3a3fab3dcd46
indicator-implementer is an agent published in the GitHub repository Mario-SO/ohlcv (23 stars, last pushed 3d ago), licensed MIT. It adds 294 tokens to every session and 1,125 once invoked, about $0.0015 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 agents, from other repositories
datahub-guide
Phase 9 of the DataHub migration exposes the terminal's in-process pub/sub layer directly to LLM tool callers through four generic MCP tools. Everything streaming into any active widget — quotes, order books, news, vessel tracks, broker ticks, geopolitical events, agent outputs, LLM token streams — is observable from…
literature-scout
经济金融学术文献侦察子智能体。负责系统性检索、筛选和分析学术文献,构建引文网络,识别研究缺口。与 generator-reviewer 分离原则:scout 只负责侦察,不参与评分和写作。.
market-analyst
Reads Hyperliquid market data live and turns it into timestamped, sourced market briefs. Read-only.
research-analyst
Fundamentals, news, catalysts, onchain and social context for anything the desk trades. Read-only, source-led, sceptical.
agentic-workflows
Agent "agentic-workflows" from rustledger/rustledger, covering github agentic workflows agent, what this agent does, files this applies to, problems this solves and how to use.
desk-lead
Runs the Hyperliquid trading desk. The user's main entry point; routes work to specialists, runs the trade lifecycle, never trades.