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 skills/mayank-io/mstack/surface-usage-patternsnpx skills add mayank-io/mstack --skill surface-usage-patternsgit clone --depth 1 https://github.com/mayank-io/mstackWhat 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 | $0.00067 | $0.00916 |
| Opus 5 | $0.00034 | $0.00458 |
| Sonnet 5 | $0.00013 | $0.00183 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
surface-usage-patterns scanned grade A with 1 finding 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find ~/.claude/projects -name "*.jsonl" -type f 2>/dev/null | head -100 Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Surface Usage Patterns
Analyze all Claude Code sessions on this computer to identify usage patterns and improvement opportunities.
Step 1: Gather Session Data
Scan all Claude Code session data. Sessions are stored in ~/.claude/projects/ as JSONL files.
# Find all session directories and conversation files
find ~/.claude/projects -name "*.jsonl" -type f 2>/dev/null | head -100
Also check for:
~/.claude/for any global configuration and history- Project-level
.claude/directories for project-specific patterns
Read a representative sample of recent sessions (at least 10-20) to understand what the user does across projects.
Step 2: Analyze Usage Patterns
For each session, extract:
- What task was performed (bug fix, feature, refactor, research, DevOps, etc.)
- Which tools were used most (Bash, Read, Edit, Write, Agent, WebSearch, etc.)
- Which skills/commands were invoked (
/commit,/review-pr, custom skills, etc.) - Repetitive multi-step workflows (sequences of actions that recur across sessions)
- Common pain points (retries, corrections, clarifications that suggest friction)
- Projects worked on and their domains
Step 3: Produce the Report
Present a structured breakdown with the following sections:
Most Frequent Activities
Rank the top activities by frequency. Include:
- Category (e.g., "Code review", "Feature implementation", "Debugging")
- Approximate frequency (daily, weekly, occasional)
- Typical workflow steps involved
Candidates for Skills
Identify workflows that should become reusable skills. A good skill candidate:
- Is a multi-step workflow that repeats across sessions or projects
- Has a consistent pattern but isn't currently codified
- Would benefit from documented best practices and guardrails
For each candidate, provide:
- Name: Suggested skill name (kebab-case)
- Trigger: When this skill should activate
- Current workflow: What the user does today (steps)
- Improvement: What the skill would standardize or automate
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 · 101 lines · 67 tokens per session scan A 9217ccaee69e
surface-usage-patterns is a skill published in the GitHub repository mayank-io/mstack (5 stars, last pushed 7d ago), licensed MIT. It adds 67 tokens to every session and 916 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…