hyalo: Skill for Claude Code

.claude/skills/dogfood/SKILL.md

dogfood is a skill for Claude Code from ractive/hyalo. It costs 102 tokens per session (1,956 once invoked), scanned A, original, MIT.

A testing procedure for hyalo, a command-line tool that works with knowledge bases. Dogfooding means using a tool on real tasks to uncover bugs and usability problems.

In plain words
What is it for?
Use it to build hyalo, review changes and earlier findings, exercise it with sources such as MDN and GitHub Docs, try realistic edge cases, and record results.
Why use it?
It tests recent changes against real documentation and knowledge bases, checks previous fixes, measures performance, and produces a structured report.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: positional $N argument.

This is ractive/hyalo's own configuration. It tells Claude Code how to work on hyalo 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 hyalo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ractive/hyalo. 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/ractive/hyalo/main/.claude/skills/dogfood/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ractive/hyalo

Made for: Claude Code.

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 dogfood

README.md
[![agentmods](https://agentmods.dev/badge/skills/ractive/hyalo/dogfood/github.svg)](https://agentmods.dev/skills/ractive/hyalo/dogfood)
Your own site
<a href="https://agentmods.dev/skills/ractive/hyalo/dogfood"><img src="https://agentmods.dev/badge/skills/ractive/hyalo/dogfood/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 dogfood

Your own site · 80×15
<a href="https://agentmods.dev/skills/ractive/hyalo/dogfood"><img src="https://agentmods.dev/badge/skills/ractive/hyalo/dogfood.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,956 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00102 $0.01956
Opus 5 $0.00051 $0.00978
Sonnet 5 $0.00020 $0.00391
Haiku 4.5 $0.00010 $0.00196

Measured 5d ago against content hash fb2503d2a60e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dogfood 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 5d 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.

.claude/skills/dogfood/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dogfood Session

A dogfood session exercises hyalo against real knowledgebases to find bugs, verify fixes, assess UX, and discover improvement opportunities. Sessions should feel like a real user working with the tool — not a mechanical checklist. Be curious, follow interesting leads, try edge cases that occur to you naturally.

Phase 1: Prepare

  1. Build and install from source, then prove the hyalo on PATH is this tree. The PATH binary is a cargo install and goes stale silently: on 2026-09-04 it was three days and eleven PRs behind target/release/hyalo, and a DEC-284 check against it nearly got filed as a bug.
    cargo build --release
    cargo install --path crates/hyalo-cli --target-dir target --force
    test "$(hyalo --version | awk '{print $3}' | tr -d '(' | sed 's/+dirty$//')" = "$(git rev-parse --short=12 HEAD)" \
      && echo "hyalo on PATH is HEAD" || { echo "STALE hyalo on PATH: $(which hyalo)"; exit 1; }
    
    --target-dir target reuses the release build so the install takes seconds; the version string is hyalo X.Y.Z (<12-char hash>[+dirty] <date>), and +dirty is fine — it only means uncommitted edits such as the report you are about to write. If the check fails, fix the PATH before doing anything else — every later command in this skill, and every explorer agent you spawn, must run the same binary. Never fall back to ./target/release/hyalo for some commands and hyalo for others in one session.
  2. Find the last dogfood report to establish the baseline:
    hyalo find --tag dogfooding --sort date --reverse --limit 1 --format text
    
    Read it to learn: which version was tested, which bugs were found, what was verified.
  3. Discover what changed since then: Use git log --oneline from that report's date to HEAD. Look for merged iteration branches (iter-N/...). For each, read the iteration file in the knowledgebase to understand what was implemented:
    hyalo find --tag iteration --property "date>=YYYY-MM-DD" --sort date --format text
    
    Then hyalo read <iteration-file> --format text for each to understand the features, bug fixes, and UX changes. These are your priority test targets.
  4. Check prior dogfood reports for open bugs to re-verify:
    hyalo find --tag dogfooding --sort date --reverse --limit 5 --format text
    
    Read the most recent reports and collect any bugs marked as found (not yet verified fixed).
  5. Pick target knowledgebases: Use a mix of:
    • Own KB (hyalo-knowledgebase/, ~250 files) — well-structured, has schemas/views
    • MDN Web Docs (../mdn/files/en-us/, ~14K files) — large, stress-tests performance
    • GitHub Docs (../docs/content/, ~3.5K files) — complex nested YAML frontmatter
    • VS Code Docs (../vscode/, ~1K files) — mid-size, different structure

Read the full file on GitHub · 181 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. 5d ago Changed · +14 lines fb2503d2a60e
  2. 11d ago First seen · 167 lines · 102 tokens per session scan A 1af4f0d5e48a

Subscribe to this mod's changes

dogfood is a skill published in the GitHub repository ractive/hyalo (24 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 1,956 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.