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/text-processingnpx skills add bug-ops/zeph --skill text-processinggit 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 | $0.00079 | $0.02415 |
| Opus 5 | $0.00039 | $0.01208 |
| Sonnet 5 | $0.00016 | $0.00483 |
| Haiku 4.5 | $0.00008 | $0.00242 |
Grade A, and why
text-processing 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Text Processing
Before running commands, detect the OS and load the matching reference for platform-specific syntax and gotchas:
- Linux —
references/linux.md(GNU sed/awk/sort with extended flags) - macOS —
references/macos.md(BSD sed/awk/sort, Homebrew GNU alternatives) - Windows —
references/windows.md(PowerShell: Select-String, Import-Csv, ForEach-Object)
OS detection:
uname -s 2>/dev/null || echo Windows
Key platform difference: sed -i syntax varies — check the OS reference before in-place edits.
Quick Reference
| Task | Portable command |
|---|---|
| Find and replace (stdout) | sed 's/old/new/g' file |
| Extract column | awk '{print $2}' file |
| Cut field (delimited) | cut -d',' -f2 file |
| Sort lines | sort file |
| Unique lines | sort file | uniq |
| Count lines/words/chars | wc -lwc file |
| Translate characters | tr 'a-z' 'A-Z' < file |
| First N lines | head -n 10 file |
| Last N lines | tail -n 10 file |
sed — Stream Editor
Substitution (portable)
# Replace first occurrence per line
sed 's/foo/bar/' file.txt
# Replace all occurrences per line
sed 's/foo/bar/g' file.txt
# Use different delimiter (when pattern contains /)
sed 's|/usr/local|/opt|g' file.txt
# Replace on specific lines
sed '5s/foo/bar/g' file.txt # line 5 only
sed '10,20s/foo/bar/g' file.txt # lines 10-20
sed '/pattern/s/foo/bar/g' file.txt # lines matching pattern
# Extended regex (-E works on both GNU and BSD)
sed -E 's/([a-z]+)_([a-z]+)/\2_\1/g' file.txt
# Capture groups (BRE)
sed 's/\(.*\)=\(.*\)/\2=\1/' file.txt
Deletion (portable)
sed '/pattern/d' file.txt # delete matching lines
sed '5d' file.txt # delete line 5
sed '10,20d' file.txt # delete range
sed '/^$/d' file.txt # delete empty lines
sed '/pattern/!d' file.txt # delete NON-matching
Print and Extract (portable)
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 · 255 lines · 79 tokens per session scan A a8a644274090
text-processing is a skill published in the GitHub repository bug-ops/zeph (57 stars, last pushed 7d ago), licensed MIT. It adds 79 tokens to every session and 2,415 once invoked, about $0.0004 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
data_analyst
Analyses datasets with professional rigour — statistical summaries, clear narratives, and well-chosen visualisations.
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.
lint-js
Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).
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.