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/lis186/sourceatlas/patternnpx skills add lis186/SourceAtlas --skill patterngit clone --depth 1 https://github.com/lis186/SourceAtlasWhat 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 | $0.00010 | $0.02425 |
| Opus 5 | $0.00005 | $0.01213 |
| Sonnet 5 | $0.00002 | $0.00485 |
| Haiku 4.5 | $0.00001 | $0.00243 |
Grade A, and why
pattern 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.
How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SourceAtlas: Pattern Learning Mode
Constitution: ANALYSIS_CONSTITUTION.md v1.0
Context
Pattern requested: $ARGUMENTS Goal: Learn how THIS specific codebase implements the requested pattern Time Limit: 5-10 minutes maximum
Quick Start
- Check cache (skip if
--forceflag present) - Detect pattern using
find-patterns.shscript - Apply output mode (--brief / --full / smart)
- Analyze top 2-3 files (high-entropy priority)
- Extract conventions and best practices
- Generate implementation guide
- Verify output using verification-guide.md
- Auto-save to
.sourceatlas/patterns/
Your Task
You are analyzing how THIS codebase implements a specific pattern by:
- Finding 2-3 best example files
- Extracting design patterns and conventions
- Providing actionable implementation guidance
Output Modes
| Parameter | Behavior | Use Case |
|---|---|---|
--brief |
List files only | Quick file browser |
--full |
Analyze all files | Deep learning |
| (default) | Smart: ≤5 files→full; >5→selection UI | Balanced |
Core Workflow
Execute these steps in order. See workflow.md for complete details.
Step 0: Parse Output Mode (10 seconds)
Purpose: Determine how much analysis to perform.
Detect flags:
--brief→ List files only, no analysis--full→ Analyze all found files- No flag → Smart mode (adapt based on file count)
→ See workflow.md#step-0
Step 1: Execute Pattern Detection (1-2 minutes)
Purpose: Find relevant files using optimized search.
Use find-patterns.sh script first:
# Locate script (global → local)
if [ -f ~/.claude/scripts/atlas/find-patterns.sh ]; then
SCRIPT_PATH=~/.claude/scripts/atlas/find-patterns.sh
elif [ -f scripts/atlas/find-patterns.sh ]; then
SCRIPT_PATH=scripts/atlas/find-patterns.sh
fi
bash "$SCRIPT_PATH" "$ARGUMENTS"
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 364 lines · 0 tokens per session scan A b0aee1b87a3f
pattern is a skill published in the GitHub repository lis186/SourceAtlas (46 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 2,425 once invoked, about $0.0001 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 2026-08-30.
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…