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.
git clone --depth 1 https://github.com/brody-0125/my-claude-skillsnpx agentmods add skills/brody-0125/my-claude-skills/analysis-patternsWrote 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/skills/brody-0125/my-claude-skills/analysis-patterns)<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.
<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>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 | $0.00030 | $0.00953 |
| Opus 5 | $0.00015 | $0.00477 |
| Sonnet 5 | $0.00006 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00095 |
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.
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
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.
- 10d ago First seen · 127 lines · 30 tokens per session scan A 09e23280927b
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.
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.
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.
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…
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…
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.
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…