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 skills add byronxlg/skillfold --skill file-managementgit clone --depth 1 https://github.com/byronxlg/skillfoldWrote 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/skills/byronxlg/skillfold/file-management)<a href="https://agentmods.dev/skills/byronxlg/skillfold/file-management"><img src="https://agentmods.dev/badge/skills/byronxlg/skillfold/file-management/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/byronxlg/skillfold/file-management"><img src="https://agentmods.dev/badge/skills/byronxlg/skillfold/file-management.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00015 | $0.00369 |
| Opus 5 | $0.00008 | $0.00185 |
| Sonnet 5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
file-management 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 9d 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.
What it actually says
File Management
You read, create, edit, and organize files and directories as part of your workflow. You handle file operations carefully and verify results.
Principles
- Always verify a file exists before attempting to read or modify it
- Create parent directories before writing files into them
- Use absolute paths when precision matters; relative paths when portability matters
- Back up or verify before destructive operations (overwrites, deletes, moves)
- Respect the project's existing directory structure and naming conventions
Reading Files
- Read files to understand their contents before making changes
- For large files, read specific sections rather than loading the entire file
- Check file encoding when dealing with non-text content
- Verify file paths are correct before acting on file contents
Creating and Writing Files
- Create directories with
mkdir -pto handle nested paths safely - Write files atomically when possible - write to a temp file then rename
- Set appropriate permissions on newly created files
- Include necessary headers, imports, or boilerplate expected by the project
Editing Files
- Read the current contents before editing to understand context
- Make targeted edits - change only what needs to change
- Preserve existing formatting, indentation, and line endings
- Verify the edit produced the expected result
Organizing
- Group related files in directories by function or domain
- Follow the project's existing naming conventions (casing, separators, extensions)
- Keep directory hierarchies shallow - deep nesting makes navigation harder
- Remove empty directories and unused files to reduce clutter
Output
Perform file operations carefully, verifying each step. Report what was created, modified, or deleted. If an operation fails, explain why and suggest alternatives.
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.
- 9d ago First seen · 49 lines · 15 tokens per session scan A 87e0aad87be4
file-management is a skill published in the GitHub repository byronxlg/skillfold (12 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 369 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
lang-typescript
TypeScript toolchain: ESLint, tsc, Jest/Vitest, npm. CI gate commands, file layout, type standards, Node 20. Use when working on a TypeScript or JavaScript project.
typescript
Apply when writing TypeScript code. Strict types, discriminated unions, async patterns, and runtime safety.
migrate-to-shoehorn
Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data.
writing-great-skills
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
solid-generic
Use when building CLI tools, libraries, scripts, hooks, or non-framework TypeScript code (Bun/Node.js -- SOLID, files < 100 lines, JSDoc mandatory).
generating-typescript-types-from-apis
Generates TypeScript interfaces from API responses or OpenAPI schemas. Use when the user asks about typing API responses, creating interfaces from JSON, parsing Swagger/OpenAPI, or keeping types in sync with backend.