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 instructions/balgaly/skit/claude-mdgit clone --depth 1 https://github.com/balgaly/skitWrote 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/instructions/balgaly/skit/claude-md)<a href="https://agentmods.dev/instructions/balgaly/skit/claude-md"><img src="https://agentmods.dev/badge/instructions/balgaly/skit/claude-md.svg" alt="Measured on agentmods" 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 | $0.00717 | $0.00717 |
| Opus 5 | $0.00358 | $0.00358 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
skit CLAUDE.md 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 4d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skit
A cross-platform package manager for AI agent skills.
Project Info
- Name: skit
- Type: npm CLI package (Node.js)
- Entry point:
bin/skit.js - Source:
src/ - Tests:
tests/ - Design spec:
docs/design.md
Code Standards
- Node.js (no TypeScript in v1 — ship fast, add types later)
- Use
const/let, nevervar - CommonJS (
require/module.exports) for maximum Node.js compatibility - Validate all user inputs (URLs, paths, skill names)
- Handle errors gracefully with clear user-facing messages
- No exposed secrets or API keys
- Follow DRY principle
- Meaningful variable and function names
Architecture
src/commands/— one file per CLI command, each exports a functionsrc/core/— shared business logic (manifest, linker, git, scanner, importer)src/agents/— pluggable agent adapters (claude-code, cursor; add new ones with ~20 lines)bin/skit.js— entry point, wires commands to commander
src/ui/is planned (picker, spinner, formatting helpers) but not yet extracted. UI logic (chalk, inquirer, ora) is currently inline in each command file.
Dependencies (keep minimal)
commander— CLI arg parsinginquirer— interactive promptschalk— terminal colorsora— spinners
Cross-Platform
- MUST work on Windows, macOS, and Linux
- Windows: use NTFS junctions (
fs.symlinkSyncwith'junction') - macOS/Linux: use directory symlinks (
fs.symlinkSyncwith'dir') - Always use
path.resolve()for absolute paths (junctions require it on Windows) - Always use
path.join()for path construction, never string concatenation - Test with forward slashes in tests, but never assume slash direction in code
Git Conventions
- Conventional commits:
feat:,fix:,refactor:,test:,docs:,chore: - Work on feature branches, merge to master
- Include
Co-Authored-By: Claude <[email protected]>in commits
Testing
- Test framework: Node.js built-in test runner (
node --test) - Use temp directories for integration tests
- Mock git operations where possible
- Test cross-platform linking behavior
- Every command gets at least basic happy-path + error-path tests
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.
- 4d ago First seen · 82 lines · 717 tokens per session scan A e9771f62031c
skit CLAUDE.md is an instructions file published in the GitHub repository balgaly/skit (2 stars, last pushed 4d ago), licensed ISC. It adds 717 tokens to every session, about $0.0036 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 instructions, from other repositories
agent-skills GEMINI.md
Gemini CLI instructions for mongodb/agent-skills, covering mongodb gemini extension and configuration.
agent-skills AGENTS.md
AGENTS.md instructions for tech-leads-club/agent-skills, covering agents.md, workflow orchestration, 1. plan mode default, 2. subagent strategy and 3. verification before done.
memory-bridge AGENTS.md
AGENTS.md instructions for jiabaobei/memory-bridge, covering agents.md — 记忆桥项目规约（ai 协作会话必读）, 版本与发布（硬性规则，所有者 2026-08-29 定）, 架构铁律 and 工程习惯.
fast-mcp-telegram CLAUDE.md
Claude Code instructions for leshchenko1979/fast-mcp-telegram, covering fast-mcp-telegram, session corrections and 2026-05-27.
obsidian-mcp-rs CLAUDE.md
Instructions for MrRefactoring/obsidian-mcp-rs, covering claude.md, commands, build / run, tests and lint gates enforced by ci (.github/workflows/ci.yml).
pioneer AGENTS.md
AGENTS.md instructions for pioneerdotai/pioneer, covering database architecture, runtime model, scheduling classes, never hold database capacity during other work and transactions and batches.