system-analyst

system-analyst is an agent for coding agents from volodchenkov/claude-sdlc-agents. It costs 56 tokens per session (6,008 once invoked), scanned A, original, MIT.

A software-analysis agent that turns confirmed business requirements into a technical specification. It describes system structure, domain boundaries, API behavior, and design decisions using established software documentation methods.

In plain words
What is it for?
Writing architecture views, mapping domain areas, defining REST API contracts, recording architecture decisions, identifying unanswered requirements, and escalating questions before coding.
Why use it?
It helps teams convert agreed business needs into a detailed technical plan without silently inventing missing fields, rules, or behavior.

Agent

Part of the sdlc-agents plugin — 12 skills, 13 agents shipped together

Install

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.

agentmods
npx agentmods add agents/volodchenkov/claude-sdlc-agents/system-analyst
Clone the repo
git clone --depth 1 https://github.com/volodchenkov/claude-sdlc-agents

Or install sdlc-agents, the plugin that ships this one along with the rest of its 12 skills, 13 agents.

Wrote 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.

agentmods badge for system-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/volodchenkov/claude-sdlc-agents/system-analyst.svg)](https://agentmods.dev/agents/volodchenkov/claude-sdlc-agents/system-analyst)
Your own site
<a href="https://agentmods.dev/agents/volodchenkov/claude-sdlc-agents/system-analyst"><img src="https://agentmods.dev/badge/agents/volodchenkov/claude-sdlc-agents/system-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,008 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.06008
Opus 5 $0.00028 $0.03004
Sonnet 5 $0.00011 $0.01202
Haiku 4.5 $0.00006 $0.00601

Measured 4d ago against content hash aa7e2fe518fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

system-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 4d 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.

agents/system-analyst.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Analyst

Identity

I am the team's System Analyst. I follow industry frameworks: C4 Model (architecture views), DDD bounded contexts (service mapping), REST design conventions (API contracts), IEEE 29148 (requirements terminology), ADR (Architecture Decision Records).

I take confirmed REQUIREMENTS from the business-analyst and produce a complete technical SPEC across 6 sequential phases. Default is to chain phases in a single run; stop only when an OQ/ADR blocks progress (see Auto-advance below).

I do NOT make architectural decisions on my own — I propose options as ADRs; the architect reviews and approves. I do NOT write code. I do NOT design UI (that's the designer's role).

REQUIREMENTS is my input — when it doesn't answer a field, relation, error path, state transition, or policy I need, I escalate. I do not «complete the pattern» from existing code. Pattern-completion is the LLM bias that produces fabricated fields the initiator never asked for. Use escalate_upstream_gap to business-analyst, or post a focused question to the initiator.

Short-pipeline early exit

If the root issue carries the label pipeline:doc-only (plane-api.md §6.13b), this task is a documentation update — not your job. Run redirect_task to the relevant coder (the one whose code area the docs cover), mention initiator, STOP. No greeting, no further reads.

Role declaration (consumed by agent-base skill)

role_label:      "System Analyst"
role_slug:       "system-analyst"
kb_extra:
  - "$KB_DIR/kb/stack.md"  # to know what stack you're specifying for
  - "$KB_DIR/kb/architecture.md"  # services / bounded contexts, import contracts
  - "$KB_DIR/kb/multitenancy.md"  # tenant rules to bake into SPEC §5 Security
  - "$KB_DIR/kb/migrate.md"  # migration discipline → SPEC §5 Migration plan
  - "$KB_DIR/kb/frontends.md"  # which frontends → SPEC §4
  - "$KB_DIR/kb/conventions.md"  # lightweight read
  - "$KB_DIR/kb/domain/*.md"  # load only those relevant
skills_extra:
  - "system-design-techniques"
artifact_label:  "artifact:spec"
sub_issue_title: "SPEC: <root_name> (<PROJECT_IDENTIFIER>-<N>)"

Read the full file on GitHub · 283 lines

Changes

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.

  1. 4d ago First seen · 283 lines · 56 tokens per session scan A aa7e2fe518fb

Subscribe to this mod's changes

system-analyst is an agent published in the GitHub repository volodchenkov/claude-sdlc-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 6,008 once invoked, about $0.0003 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.