analysis-patterns

analysis-patterns is a skill for Claude Code from brody-0125/my-claude-skills. It costs 30 tokens per session (953 once invoked), scanned A, original, MIT.

A collection of reusable methods for studying how coding agents use tools, such as detecting repeated actions, unusual behaviour, and signs of improvement.

In plain words
What is it for?
Use it to analyse agent sessions, find wasted calls or failed retries, score unusual activity, and extract signals for workflow improvements.
Why use it?
It gives teams consistent ways to spot inefficient tool use and identify patterns linked to better or worse results.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions subagents.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is [improvement-pipeline.md](../plugin-introspector/resources/improvement-pipeline.md) Layer 2..

Part of the plugin-introspector plugin — 4 skills shipped together

Good fit Use it to analyse agent sessions, find wasted calls or failed retries, score unusual activity, and extract signals for workflow improvements.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/brody-0125/my-claude-skills
agentmods
npx agentmods add skills/brody-0125/my-claude-skills/analysis-patterns

Made for: Claude Code.

Or install plugin-introspector, the plugin that ships this one along with the rest of its 4 skills.

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 analysis-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/brody-0125/my-claude-skills/analysis-patterns/github.svg)](https://agentmods.dev/skills/brody-0125/my-claude-skills/analysis-patterns)
Your own site
<a href="https://agentmods.dev/skills/brody-0125/my-claude-skills/analysis-patterns"><img src="https://agentmods.dev/badge/skills/brody-0125/my-claude-skills/analysis-patterns/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.

agentmods 80×15 button for analysis-patterns

Your own site · 80×15
<a href="https://agentmods.dev/skills/brody-0125/my-claude-skills/analysis-patterns"><img src="https://agentmods.dev/badge/skills/brody-0125/my-claude-skills/analysis-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 953 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00030 $0.00953
Opus 5 $0.00015 $0.00477
Sonnet 5 $0.00006 $0.00191
Haiku 4.5 $0.00003 $0.00095

Measured 10d ago against content hash 09e23280927b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

analysis-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 10d 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.

plugins/plugin-introspector/skills/analysis-patterns/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analysis Patterns — Reusable Heuristics

Standardized analysis methods used by multiple agents.

Tool Sequence Patterns

Productive Sequences (high correlation with quality score ≥4)

Pattern Description Expected Token Cost
Read→Edit→Bash(pass) Read file, edit, verify ~1500 tokens
Glob→Read→Edit Find file, read, edit ~1800 tokens
Read→Task(sub)→Edit Read, delegate, apply ~2500 tokens

Anti-Patterns (high correlation with quality score ≤3)

Pattern Description Token Waste
Read→Read→Read(same) Repeated reads of same file ~1000 tokens/repeat
Bash(fail)→Bash(fail)→Edit Build-before-edit ~800 tokens wasted
Edit→Bash(fail)→Edit→Bash(fail) Edit-test loop without reading error ~1500 tokens/cycle

Statistical Methods

Z-Score Calculation

z = (x - μ) / σ
Threshold: |z| > 2.0 → anomaly
Minimum data points: 5 (for reliable σ)

Moving Average

MA(n) = sum(last_n_values) / n
Window: 5 sessions (default)
Alert if: current > MA × 1.5

Efficiency Ratio

efficiency = productive_calls / total_calls
productive_call = call that contributed to final output (no retry, no revert)
Target: ≥ 0.85

Token Estimation Baselines

Expected token usage per tool (for waste detection):

Tool Expected Range Flag If
Read 200-1500 >2000 (large file, use offset)
Edit 100-500 >800 (complex edit, consider split)
Write 200-2000 >3000 (generated file too large)
Bash 50-500 >1000 (verbose output, use --quiet)
Glob 50-200 >500 (too many matches)
Grep 50-300 >800 (broad search pattern)
Task 500-5000 >8000 (sub-agent context explosion)

Plugin Phase Patterns

Phase detection and per-plugin baselines are loaded dynamically from plugin profiles: ~/.claude/plugin-introspector/plugin-profiles/{plugin}/profile.json

Read the full file on GitHub · 127 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. 10d ago First seen · 127 lines · 30 tokens per session scan A 09e23280927b

Subscribe to this mod's changes

analysis-patterns is a skill published in the GitHub repository brody-0125/my-claude-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 953 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

self-audit

Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.

SpaiR/task-pipeline · 52 tokens

grill

Interrogate a plan or decision one question at a time before capture, keeping a decision-plus-rationale ledger, then route to the right capture skill.

SpaiR/task-pipeline · 33 tokens

architect

Answer build-or-adopt honestly, then design one committed architecture from your own understanding of the problem — driven by ranked quality attributes, stress-tested against the field and against change, proven by a walking skeleton, its consequences confirmed by the user, committed to ARCHITECTURE.md. A command the…

donald-ada/workinggenius · 80 tokens

designer

Settle the look before the pixels — audience and context first, then the base and the delta, taste settled by looking at real states, accessibility as the floor, one design language committed to DESIGN.md as tokens with roles. A command the user types, for work with an interface someone will see; standalone, no other…

donald-ada/workinggenius · 69 tokens

compact

Put the compaction question to a snapshot that drifted — route what no longer constrains unfinished work, and say what moves before moving it. In flight or done; the log is appended to, never edited or trimmed.

donald-ada/workinggenius · 47 tokens

errata

Correct what was written wrong — the binding line rewritten in place, the record it came from appended to and never touched, both carrying the evidence that overturned it. Use when a run, a file, or the user contradicts something already written in a work file, a plan's contract, the glossary, or the decision index…

donald-ada/workinggenius · 92 tokens