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/bug-ops/zeph/file-opsnpx skills add bug-ops/zeph --skill file-opsgit clone --depth 1 https://github.com/bug-ops/zephWhat 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 | $0.00090 | $0.02345 |
| Opus 5 | $0.00045 | $0.01172 |
| Sonnet 5 | $0.00018 | $0.00469 |
| Haiku 4.5 | $0.00009 | $0.00234 |
Grade A, and why
file-ops 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File Operations
Before running any file system command, detect the user's OS and load the matching reference for platform-specific syntax:
- Linux —
references/linux.md(GNU coreutils, grep, find, ripgrep, fd) - macOS —
references/macos.md(BSD find/stat/sed, Spotlight, Homebrew tools) - Windows —
references/windows.md(PowerShell: Get-ChildItem, Select-String, Get-Content)
OS detection:
uname -s 2>/dev/null || echo Windows
Path specification
Relative vs absolute
| Syntax | Meaning |
|---|---|
. |
Current working directory |
.. |
Parent directory |
./src |
src/ relative to cwd |
../../config |
Two levels up, then into config/ |
/home/user/project |
Absolute path (Unix) |
C:\Users\user\project |
Absolute path (Windows) |
~/Documents |
Home directory shortcut (Unix shells expand ~) |
Quoting paths with spaces
Paths containing spaces, parentheses, or special characters must be quoted:
"./my project/src"— double quotes (variables expand inside)'./my project/src'— single quotes (literal, no expansion)./my\ project/src— backslash escaping per character
Trailing slash behavior
path/to/dir— refers to the directory itselfpath/to/dir/— refers to the contents (relevant forrsync,cp -r, tab completion)
Glob patterns
Globs are shell-level filename matching patterns. They do NOT use regex syntax.
| Pattern | Matches | Does not match |
|---|---|---|
* |
any sequence of characters (except /) |
nothing across directories |
? |
exactly one character | empty string |
[abc] |
one of a, b, or c |
d, ab |
[a-z] |
one lowercase letter | A, 1 |
[!abc] or [^abc] |
any char except a, b, c |
a |
** |
any depth of directories (in tools that support it) | — |
Common glob examples
| Task | Pattern |
|---|---|
| All Rust source files | *.rs |
| All TOML configs | *.toml |
| All test files | *_test.* or test_*.* |
| All hidden files | .* |
All files in src/ subtree |
src/**/* (requires ** support) |
| Images by extension | *.{png,jpg,svg} (brace expansion, bash/zsh) |
| Single-char extension | *.? |
Files starting with config |
config* |
| Logs with date suffix | app-2025-??-??.log |
What ships with it
3 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 · 222 lines · 90 tokens per session scan A 908f560321b4
file-ops is a skill published in the GitHub repository bug-ops/zeph (57 stars, last pushed 8d ago), licensed MIT. It adds 90 tokens to every session and 2,345 once invoked, about $0.0005 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
verify
Run Chimeraforge's canonical verification gate end-to-end and report the real output before claiming work done or committing. Failing output gets pasted, fixed, and re-run — never summarized away.
free-model-manager
Free AI model management - discover, download, and manage free/open-source AI models from Ollama, HuggingFace, and other sources.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.