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/trtmn/agent-plugins/touch_filenpx skills add trtmn/agent-plugins --skill touch_filegit clone --depth 1 https://github.com/trtmn/agent-pluginsWhat 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 | $0.00108 | $0.00569 |
| Opus 5 | $0.00054 | $0.00284 |
| Sonnet 5 | $0.00022 | $0.00114 |
| Haiku 4.5 | $0.00011 | $0.00057 |
Grade A, and why
touch_file 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 yesterday.
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
touch_file
When a Write or Edit tool call fails while trying to create a new file, recover by using touch via the Bash tool to create the empty file first, then retry the Write.
Why this matters
The Write tool can fail when creating new files — often because parent directories don't exist, or the filesystem needs the file to be created differently. Rather than giving up or trying workarounds, a quick mkdir -p + touch reliably sets up the file path so the Write tool succeeds on retry.
Recovery steps
When Write or Edit fails on a new file (not an existing one):
- Create parent directories — run
mkdir -p <parent-directory>via Bash to ensure the full directory path exists. - Create the empty file — run
touch <filepath>via Bash. - Retry the Write — use the Write tool again with the same content. It should succeed now.
You can combine steps 1 and 2:
mkdir -p src/utils && touch src/utils/helpers.ts
When this applies
- A Write tool call fails and the target file does not already exist
- The error mentions missing directories, file not found, or path issues
- You're trying to create a file in a nested directory structure
Edge case: broken symlinks
If mkdir -p fails because a broken symlink occupies a path component (error like No such file or directory even though mkdir -p should create it), the symlink is pointing to a nonexistent target and blocking directory creation. Do not remove it automatically — the symlink may be there intentionally. Instead, tell the user what you found and ask how they'd like to proceed (e.g., remove the symlink, fix its target, or choose a different path).
When this does NOT apply
- Edit or Write fails on a file that already exists — that's a different problem
- The error is unrelated to file creation (e.g., permission denied on an existing file, disk full)
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.
- yesterday First seen · 46 lines · 108 tokens per session scan A 9dcab96af295
touch_file is a skill published in the GitHub repository trtmn/agent-plugins (2 stars, last pushed 5d ago), licensed Unlicense. It adds 108 tokens to every session and 569 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 2026-08-31.
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…