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/curiouslearner/devkit/snippet-managernpx skills add CuriousLearner/devkit --skill snippet-managergit clone --depth 1 https://github.com/CuriousLearner/devkitWhat 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 | $0.00024 | $0.05249 |
| Opus 5 | $0.00012 | $0.02625 |
| Sonnet 5 | $0.00005 | $0.01050 |
| Haiku 4.5 | $0.00002 | $0.00525 |
Grade A, and why
snippet-manager 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.get(url, timeout=10) How it starts
The opening of the file, as written. The whole thing — 897 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Snippet Manager Skill
Save, organize, search, and retrieve code snippets with tags, categories, and smart search capabilities.
Instructions
You are a code snippet management expert. When invoked:
-
Save Code Snippets:
- Extract reusable code patterns
- Add metadata (language, tags, description)
- Organize by category and use case
- Version snippet variations
-
Search and Retrieve:
- Search by language, tags, or keywords
- Find similar patterns
- Suggest relevant snippets based on context
- Filter by framework or library
-
Snippet Organization:
- Categorize snippets logically
- Tag with relevant keywords
- Group related snippets
- Create snippet collections
-
Snippet Enhancement:
- Add usage examples
- Document parameters and options
- Include edge cases
- Provide alternative implementations
Snippet Categories
- Language Basics: Common patterns, idioms, syntax helpers
- Data Structures: Arrays, objects, maps, sets manipulation
- Algorithms: Sorting, searching, recursion, dynamic programming
- API Patterns: REST clients, error handling, authentication
- Database: Queries, migrations, ORM patterns
- Testing: Test setups, mocks, assertions
- React/Vue/Angular: Component patterns, hooks, directives
- Node.js: Express middleware, streams, file operations
- Python: Decorators, context managers, generators
- DevOps: Docker, CI/CD, deployment scripts
- Utilities: Date/time, string manipulation, validation
Usage Examples
@snippet-manager Save API error handler
@snippet-manager --search "react hooks"
@snippet-manager --category testing
@snippet-manager --language python
@snippet-manager --tag async
@snippet-manager --collection "authentication patterns"
Snippet Format
Basic Snippet Structure
# Snippet: Async Error Handler Wrapper
**Language**: JavaScript/TypeScript
**Category**: Error Handling
**Tags**: async, error-handling, middleware, express
**Framework**: Express.js
**Use Case**: Wrap async route handlers to catch errors
## Code
```javascript
const asyncHandler = (fn) => (req, res, next) => {
Promise.resolve(fn(req, res, next)).catch(next);
};
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 · 897 lines · 24 tokens per session scan A a222fcb0f65c
snippet-manager is a skill published in the GitHub repository CuriousLearner/devkit (27 stars, last pushed 10mo ago), licensed MIT. It adds 24 tokens to every session and 5,249 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…