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/mckruz/claude-code-sdlc/data-analystgit clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlcWhat 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 | $0.00083 | $0.01672 |
| Opus 5 | $0.00042 | $0.00836 |
| Sonnet 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 yesterday.
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.
- yesterday 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 (4 stars, last pushed 4d ago), licensed MIT. It adds 83 tokens to every session and 1,672 once invoked, about $0.0004 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.