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 liqiongyu/lenny_skills_plus --skill dogfoodinggit clone --depth 1 https://github.com/liqiongyu/lenny_skills_plusWrote 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/liqiongyu/lenny_skills_plus/dogfooding)<a href="https://agentmods.dev/skills/liqiongyu/lenny_skills_plus/dogfooding"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/dogfooding/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/liqiongyu/lenny_skills_plus/dogfooding"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/dogfooding.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 | $0.00027 | $0.01993 |
| Opus 5 | $0.00014 | $0.00996 |
| Sonnet 5 | $0.00005 | $0.00399 |
| Haiku 4.5 | $0.00003 | $0.00199 |
Grade A, and why
dogfooding 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 12d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dogfooding
Scope
Covers
- Designing and running a dogfooding loop where the product team uses the product like a real user would
- Creating "creator commitments" when the product is for creators (e.g., publish a podcast, ship a workflow, run weekly reports)
- Capturing issues as reproducible artifacts (not vibes): logs, severity, decisions, owners, and follow-through
When to use
- "Set up a dogfooding program / dogfooding sprint for our product team."
- "We’re shipping soon—make sure we’re using the product daily and fixing the biggest pain."
- "We built this for creators; our team needs to be creators to understand the workflow."
- "Create an internal beta plan and a weekly dogfooding report template."
When NOT to use
- You need to validate market demand or solve who is the customer / what is the problem (do discovery first)
- The product team cannot realistically represent the workflow (e.g., regulated roles, hardware constraints) without proxies
- You’re looking for user research replacement (dogfooding complements -- not replaces -- external user feedback)
- The only goal is "QA everything" (use a QA/test plan; dogfooding is for experience + value + workflow realism)
- You need structured usability testing with real external users, task completion metrics, and think-aloud protocols (use
usability-testing) - You’re planning the actual product launch/release rollout (use
shipping-products) - You need a design critique session to evaluate visual/interaction quality (use
running-design-reviews) - You want to build a framework for developing product taste and quality intuition (use
product-taste-intuition)
Inputs
Minimum required
- Product summary + target user persona (who it’s for; what job it does)
- 1–3 core workflows to dogfood (end-to-end)
- Time box + cadence (e.g., 1 week sprint; 20 min/day; weekly triage)
- Participants (roles) + any "creator commitments" required
- Environment constraints (prod vs staging; data/privacy constraints; access constraints)
What ships with it
13 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.
- eval/eval_config.json 1.5 KB
- eval/SHOWCASE.md 4.3 KB
- eval/with_skill.md 29 KB
- eval/without_skill.md 27 KB
- README.md 1.1 KB
- references/CHECKLISTS.md 1.8 KB
- references/EXAMPLES.md 888 B
- references/INTAKE.md 1.5 KB
- references/RUBRIC.md 2.1 KB
- references/SOURCE_SUMMARY.md 1.4 KB
- references/TEMPLATES.md 2.6 KB
- references/WORKFLOW.md 3.4 KB
- skillpack.json 354 B
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.
- 12d ago First seen · 130 lines · 27 tokens per session scan A b9b1fa79be72
dogfooding is a skill published in the GitHub repository liqiongyu/lenny_skills_plus (52 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,993 once invoked, about $0.0001 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
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
performing-api-fuzzing-with-restler
Uses Microsoft RESTler to perform stateful REST API fuzzing by automatically generating and executing test sequences that exercise API endpoints, discover producer-consumer dependencies between requests, and find security and reliability bugs. The tester compiles an OpenAPI specification into a RESTler fuzzing…