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/resetnpx skills add lis186/SourceAtlas --skill resetgit 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 | $0.00008 | $0.00651 |
| Opus 5 | $0.00004 | $0.00326 |
| Sonnet 5 | $0.00002 | $0.00130 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade C, and why
reset scanned grade C 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .sourceatlas/* How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SourceAtlas: Clear Saved Results
Context
Target: $ARGUMENTS (default: all)
Your Task
Help user clear saved analysis results from .sourceatlas/ directory.
Step 1: Check what exists
ls -la .sourceatlas/ 2>/dev/null || echo "No .sourceatlas/ directory found"
Also check subdirectories:
# Count files in each subdirectory
for dir in patterns flows impact deps; do
if [ -d ".sourceatlas/$dir" ]; then
count=$(ls -1 ".sourceatlas/$dir" 2>/dev/null | wc -l)
echo "$dir/: $count files"
fi
done
Step 2: Report findings
List what will be deleted based on target:
- If no argument or "all": list everything
- If specific target (e.g., "patterns"): list only that
Example output:
Found the following saved analyses:
- overview.yaml (2025-12-12)
- patterns/ (3 files)
- history.md (2025-12-11)
Are you sure you want to delete?
Step 3: Wait for confirmation
Ask user to confirm. Do NOT proceed without explicit confirmation.
Acceptable confirmations:
- "yes"
- "ok"
- "confirm"
- "delete"
- "sure"
- etc.
Step 4: Delete if confirmed
Based on target:
# All (default, no argument)
rm -rf .sourceatlas/*
# Specific targets
rm -f .sourceatlas/overview.yaml # for "overview"
rm -rf .sourceatlas/patterns/ # for "patterns"
rm -rf .sourceatlas/flows/ # for "flows"
rm -f .sourceatlas/history.md # for "history"
rm -rf .sourceatlas/impact/ # for "impact"
rm -rf .sourceatlas/deps/ # for "deps"
Step 5: Confirm deletion
✅ Cleared [target or ".sourceatlas/"]
If nothing to clear
.sourceatlas/ directory does not exist or is already empty
Target Reference
| Target | Path | Description |
|---|---|---|
overview |
.sourceatlas/overview.yaml |
Project overview |
patterns |
.sourceatlas/patterns/ |
Pattern analysis |
flows |
.sourceatlas/flows/ |
Flow analysis |
history |
.sourceatlas/history.md |
Temporal analysis |
impact |
.sourceatlas/impact/ |
Impact analysis |
deps |
.sourceatlas/deps/ |
Dependency analysis |
| (no argument) | .sourceatlas/* |
Clear all |
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 · 109 lines · 0 tokens per session scan C 8b2b45ad16e5
reset is a skill published in the GitHub repository lis186/SourceAtlas (47 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 651 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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…