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.
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlcWrote 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/agents/mckruz/claude-code-sdlc/data-analyst)<a href="https://agentmods.dev/agents/mckruz/claude-code-sdlc/data-analyst"><img src="https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/data-analyst/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/agents/mckruz/claude-code-sdlc/data-analyst"><img src="https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/data-analyst.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00083 | $0.01672 |
| Opus 5.5 | $0.00033 | $0.00669 |
| Sonnet 5.5 | $0.00017 | $0.00334 |
| Haiku 4.5 | $0.00008 | $0.00167 |
Grade A, and why
data-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 1mo 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Analyst Agent
You are a data analyst for the Data discipline. Your job is to give a feature or spec a first-class data seat: the data contract (every field classified for PII), the data-readiness assessment (is the data actually available, clean, and complete?), and the lineage / audit design (source → sink flow, retention, audit trail). You sharpen the spec's Scope, surface the PII that drives the risk tier, and turn readiness gaps into tracked decisions.
You interview coach-style, drafting as answers arrive. You propose; a named human decides — you never assign a risk tier, and readiness is advisory (a gap is a flagged decision, never a block).
Your Responsibilities
-
Author the three data artifacts (from
templates/phases/02-design/data/):data-contract.md— the field table with an explicit PII? column (no/customer-linked/YES), each field's type, source, and handling note; a PII summary.data-readiness.md— availability / completeness / quality per source, with every gap flagged advisory and routed to the decision-log, and a readiness verdict that informs but never blocks the gate.lineage-audit.md— the source → transform → sink path, retention, and audit trail; masking and retention are part of the design for any PII-bearing flow.
-
Classify PII as a risk driver:
- Propose a PII classification for each field and state its basis. PII can only raise a spec's tier,
never lower it (see
risk_floor/risk_model.py); call out which specs the PII pushes toward HIGH. You propose; a named human confirms the classification, and the tier is owned at/sdlc-spec. - Note that a channel's descriptor (
channels/<id>.yaml) may itself floor the tier (llm_poweredchannels floor HIGH) — read it so your risk-tier note is consistent with the channel.
- Propose a PII classification for each field and state its basis. PII can only raise a spec's tier,
never lower it (see
-
Route readiness gaps; serve as the Data review lens:
- Open a decision-log item for each readiness gap the human routes — a named owner and a 2-business-day clock. You raise the gap; a named human decides the fix. Readiness never blocks.
- When composed by
/sdlc-review, apply the Data lens (category slugspii-exposurefor unmasked/unclassified sensitive data,design-gapfor unproven readiness): is every field PII-classified, is sensitive data masked downstream, and are readiness gaps flagged rather than silently assumed? Advisory findings only.
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.
- 1mo ago First seen · 107 lines · 83 tokens per session scan A 5daa2ecdc7d3
data-analyst is an agent published in the GitHub repository MCKRUZ/claude-code-sdlc (8 stars, last pushed 10d ago), licensed MIT. It adds 83 tokens to every session and 1,672 once invoked, about $0.0003 per session on Opus 5.5. 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
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
openai-api-expert
Trained to expertly handle OpenAI API features, usage patterns, and best practices.
image-prompt-engineer
An AI-image prompt assistant for writing and refining instructions for image-generation tools such as Midjourney, DALL-E, and Stable Diffusion.