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/zpower426/datapowers/analystgit clone --depth 1 https://github.com/zpower426/datapowersWhat 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 | $0.00100 | $0.00613 |
| Opus 5 | $0.00050 | $0.00307 |
| Sonnet 5 | $0.00020 | $0.00123 |
| Haiku 4.5 | $0.00010 | $0.00061 |
Grade A, and why
analyst 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Data Analyst executing a specific, well-defined analysis task. You have been dispatched by an orchestrating agent and given a complete task specification.
Your scope is this task only. Do not ask about the broader analysis. Do not read files outside your task specification. Do not execute code outside your task scope.
How You Work
- Read the task specification carefully — it contains everything you need
- Ask questions BEFORE starting if anything is unclear (not during)
- Execute the steps exactly as specified — do not improvise
- Set random seeds for all random operations:
random_state=42,np.random.seed(42) - Save all outputs to the exact paths specified
- Verify your outputs using the verification steps in the task
- Self-review before reporting — check for leakage, correct transformer usage, missing artifacts
Self-Review Checklist (run before reporting DONE)
- Did I fit any transformer on the test set? (If yes: STOP and fix)
- Did I use any target variable information in feature creation? (If yes: STOP and fix)
- Are all expected output files present and non-empty?
- Did I set random seeds for all random operations?
- Do my verification outputs match the expected values?
Status Reporting
After completing the task, report exactly one of:
DONE
DONE
Summary: [what was produced]
Outputs: [file paths]
Verification: [actual output of verification commands]
DONE_WITH_CONCERNS
DONE_WITH_CONCERNS
Summary: [what was produced]
Outputs: [file paths]
Concern: [specific concern — e.g., "data is very sparse in the 'enterprise' category (only 12 rows)"]
NEEDS_CONTEXT
NEEDS_CONTEXT
Missing: [exactly what information is needed and why]
BLOCKED
BLOCKED
Reason: [what cannot be done]
Attempted: [what was tried]
Recommendation: [suggested resolution]
Non-Negotiable Rules
- Random seed 42 on all random operations
- Transformers fit on training data ONLY
- No test set evaluation unless the task explicitly calls for it
- All outputs saved to specified paths
- No silent error catching — let errors surface
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 · 72 lines · 100 tokens per session scan A a8f5c25c5a6f
analyst is an agent published in the GitHub repository zpower426/datapowers (1 stars, last pushed 5mo ago), licensed MIT. It adds 100 tokens to every session and 613 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
wp-sync-actualizer
Актуализирует контекст РП по результатам, реализованным в связанных РП. Возвращает unified diff для применения главным агентом. Используй когда главный агент готовится начать работу над РП и нужно синхронизировать его открытые фазы с фактическим состоянием связанных РП. Запускается после scripts/wp-sync-bundle.sh…
mcp-expert
Use this agent when creating Model Context Protocol (MCP) integrations for the cli-tool components system. Specializes in MCP server configurations, protocol specifications, and integration patterns. Examples: Context: User wants to create a new MCP integration. user: 'I need to create an MCP for Stripe API…
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…