kicad-tools: Skill for Claude Code

.agents/skills/loom-comment-body-literal-path/SKILL.md

loom-comment-body-literal-path is a skill for Claude Code, Codex from rjwalters/kicad-tools. It costs 19 tokens per session (1,362 once invoked), scanned A, original, MIT.

A reference explaining a command-line mistake when posting GitHub issue or pull-request comments from a file. In these commands, writing @path posts the text "@path" instead of reading the file.

In plain words
What is it for?
It documents the mistake, its consequences, and the correct ways to provide comment text.
Why use it?
It prevents review or issue comments from being replaced by a useless file path, including when using the GitHub command-line tool.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is rjwalters/kicad-tools's own configuration. It tells Claude Code and Codex how to work on kicad-tools itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kicad-tools configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rjwalters/kicad-tools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rjwalters/kicad-tools/main/.agents/skills/loom-comment-body-literal-path/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rjwalters/kicad-tools

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for loom-comment-body-literal-path

README.md
[![agentmods](https://agentmods.dev/badge/skills/rjwalters/kicad-tools/loom-comment-body-literal-path/github.svg)](https://agentmods.dev/skills/rjwalters/kicad-tools/loom-comment-body-literal-path)
Your own site
<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/loom-comment-body-literal-path"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/loom-comment-body-literal-path/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.

agentmods 80×15 button for loom-comment-body-literal-path

Your own site · 80×15
<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/loom-comment-body-literal-path"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/loom-comment-body-literal-path.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.01362
Opus 5.5 $0.00008 $0.00545
Sonnet 5.5 $0.00004 $0.00272
Haiku 4.5 $0.00002 $0.00136

Measured 8d ago against content hash 351a0d573759, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

loom-comment-body-literal-path 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 8d 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.

.agents/skills/loom-comment-body-literal-path/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

--body @path Does NOT Expand — It Posts the Literal String (canonical)

Single canonical copy; role prompts' short pointers refer here.

If a comment/review body you're posting (via gh issue comment, gh pr comment, or gh api ... comments) lives in a scratch/scratchpad file, do not pass it as --body @path. Unlike some shells' @file conventions, gh pr comment --body @path and gh issue comment --body @path do not read the file — they post the literal text @path as the comment. A real incident (PR #4457) lost an entire changes-requested review this way (the body was the string @/private/tmp/.../review.md; the file was overwritten before anyone caught it). It recurred again later via gh api ... -f body=@path (-f/--raw-field never expands @path either) — see #5252. The stdin spelling fails identically: --body @- and -f body=@- post the literal @- (#9258: a PR merged on an approval whose whole body was @-). Only gh api ... -F body=@- reads stdin; post-verdict.sh takes --body-file -.

❌ POSTS THE LITERAL STRING "@path" — NOT THE FILE CONTENTS
   gh pr comment 123 --body @/tmp/review-123.md
   gh pr comment 123 --body "@/tmp/review-123.md"
   gh issue comment 123 --body @/tmp/comment-123.md
   gh pr comment 123 --body @-        (stdin spelling: still the literal "@-")

❌ ALSO POSTS THE LITERAL STRING — a variable does NOT change what the flag does
   REVIEW_FILE="@/tmp/review-123.md"; gh pr comment 123 --body "$REVIEW_FILE"

❌ ALSO POSTS THE LITERAL STRING — on `gh api`, only -F/--field expands @path
   gh api repos/{owner}/{repo}/issues/123/comments -f body=@/tmp/review-123.md

✅ USE ONE OF THESE INSTEAD
   gh pr comment 123 --body "$(cat <<'EOF'
   ... review prose ...
   EOF
   )"
   gh pr comment 123 --body-file /tmp/review-123.md
   gh api repos/{owner}/{repo}/issues/123/comments -F body=@/tmp/review-123.md

Prefer the heredoc for a short/dynamic body and --body-file <path> for one that lives in a file (gh api ... -F body=@path also reads it; -f does not). --body/-b takes literal text only. After posting, re-fetch the comment (gh pr view <number> --comments) to confirm it renders your prose, not a path string.

Why <<'EOF' must stay quoted: .loom/docs/comment-body-heredoc-quoting.md.

Read the full file on GitHub · 93 lines

Changes

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.

  1. 8d ago Changed · -1 lines · -30 tokens per session 351a0d573759
  2. 24d ago First seen · 94 lines · 49 tokens per session scan A a876da413917

Subscribe to this mod's changes

loom-comment-body-literal-path is a skill published in the GitHub repository rjwalters/kicad-tools (70 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 1,362 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-24.

Related

Other skills, from other repositories