detect-patterns

A command that examines Claude Code session history for repeated sequences of actions and suggests automations.

In plain words
What is it for?
Use it to review tool-call history, classify repeated workflows, and draft automation files for your approval.
Why use it?
It helps reveal manual work you repeat and keeps proposed changes under your control before anything is created.

Command for Claude Code

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 commands/ai-sdlc-framework/ai-sdlc/detect-patterns
Clone the repo
git clone --depth 1 https://github.com/ai-sdlc-framework/ai-sdlc

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 326 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 $0.00000 $0.00326
Opus 5 $0.00000 $0.00163
Sonnet 5 $0.00000 $0.00065
Haiku 4.5 $0.00000 $0.00033

Measured 2d ago against content hash ea3ea1304045, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

detect-patterns 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.

.claude/commands/detect-patterns.md · 34 lines

What it actually says

Detect repetitive workflow patterns from Claude Code session history and propose automations.

Steps

  1. Read telemetry data from ~/.claude/usage-data/tool-sequences.jsonl
  2. Also read session metadata from ~/.claude/usage-data/session-meta/*.json for historical data
  3. Run pattern detection using the orchestrator's n-gram mining engine:
    import { readToolSequenceJSONL, mineFrequentPatterns, classifyPattern } from '@ai-sdlc/orchestrator';
    
  4. Classify each pattern as command-sequence, copy-paste-cycle, or periodic-task
  5. Generate proposals for each detected pattern with draft artifact content
  6. Present results as a table: | # | Pattern | Type | Confidence | Frequency | Sessions | Proposed Artifact |
  7. For each proposal, show the draft artifact content and ask if the user wants to approve it
  8. If approved, write the artifact file using the artifact writer

Arguments

  • --since YYYY-MM-DD — only analyze events after this date
  • --min-confidence 0.6 — minimum confidence threshold (0-1)

Important

  • Only create artifacts the user explicitly approves
  • Never overwrite existing files
  • Show the full draft content before writing
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. 2d ago First seen · 34 lines · 0 tokens per session scan A ea3ea1304045

Subscribe to this mod's changes

detect-patterns is a command published in the GitHub repository ai-sdlc-framework/ai-sdlc (92 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 326 tokens. 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.