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 chen3feng/agent-skills --skill shell-heredoc-and-multiline-stringsgit clone --depth 1 https://github.com/chen3feng/agent-skillsWrote 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/chen3feng/agent-skills/shell-heredoc-and-multiline-strings)<a href="https://agentmods.dev/skills/chen3feng/agent-skills/shell-heredoc-and-multiline-strings"><img src="https://agentmods.dev/badge/skills/chen3feng/agent-skills/shell-heredoc-and-multiline-strings/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/chen3feng/agent-skills/shell-heredoc-and-multiline-strings"><img src="https://agentmods.dev/badge/skills/chen3feng/agent-skills/shell-heredoc-and-multiline-strings.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 | $0.00031 | $0.03587 |
| Opus 5 | $0.00015 | $0.01793 |
| Sonnet 5 | $0.00006 | $0.00717 |
| Haiku 4.5 | $0.00003 | $0.00359 |
Grade C, and why
shell-heredoc-and-multiline-strings scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
(`/bin/rm -rf .agent/scratchpad/*` when convenient, or let it live — How it starts
The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-line strings through an agent shell
When to use
You need to supply a multi-line string to a command — a commit
message, a gh pr create --body, a SQL snippet — from an AI agent's
terminal tool.
Problem
Agent terminals often paste multi-line commands with subtle whitespace/newline mangling. Observed failures:
- Heredocs that silently truncate at the first embedded
'or`. $(cat <<'EOF' … EOF)producing a straycmdsubst heredoc>prompt the agent never escapes, leaving a process wedged in the background.- In zsh, wrapping a heredoc inside a double-quoted command-substitution —
gh pr create --body "$(cat <<'EOF' … EOF)"— hangs atcmdand dquote>/cmdand quote>prompts as soon as the heredoc body contains triple-backtick fences, embedded$(…), or backslashes. zsh's parser can no longer tell whether quotes are balanced and waits forever for input. Common symptom: theterminaltool reports "command was running, but the user actively interrupted" with a transcript full ofcmdand dquote>lines. - Quoted multi-line
-mstrings being split at newlines, so only the first line becomes the commit title and the rest is interpreted as extra git arguments — sometimes parsed as-cconfig keys (seeerror: key does not contain a section). - Multiple
-mflags where one flag's value contains embedded newlines (e.g.git commit -m 'title' -m 'para1' -m 'line1\nline2\nline3'). The agent terminal → shell → git chain re-interprets the real newlines inside the quoted argument: the shell sees an unclosed quote and drops into aquote>/dquote>continuation prompt, waiting forever for input. Symptom is identical to the heredoc hang: theterminaltool reports the command as running but the user has to interrupt. This failure mode persists even when each individual-mvalue looks "safe" in isolation — it only takes one multi-line value anywhere in the argv to wedge the parse.
Solution
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 · 331 lines · 31 tokens per session scan C bb18b693d10f
shell-heredoc-and-multiline-strings is a skill published in the GitHub repository chen3feng/agent-skills (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 3,587 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
github-operations
GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.
coding-standards
Repository coding standards, linters, formatters, CLI design rules, HTTP caching guidelines, and git commit message conventions (Conventional Commits). Includes scripts for formatting Python, shell, Markdown, Kotlin, JSON, and XML. Use when writing, reviewing, formatting, or linting code, verifying CLI ergonomics…
semantic-commit
A Git workflow for splitting mixed code changes into separate conventional commits. Conventional commits use a predictable format such as feat, fix, or test to describe each change.
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
github-pr-description
Generate and create pull request descriptions automatically using GitHub CLI. Use when the user asks to create a PR, generate a PR description, make a pull request, or submit changes for review. Analyzes git diff and commit history to create comprehensive, meaningful PR descriptions that explain what changed, why it…
git-commit
Generate well-formatted git commit messages following conventional commit standards.