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/fagemx/prismstack/dogfoodnpx skills add fagemx/prismstack --skill dogfoodgit clone --depth 1 https://github.com/fagemx/prismstackWrote 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/fagemx/prismstack/dogfood)<a href="https://agentmods.dev/skills/fagemx/prismstack/dogfood"><img src="https://agentmods.dev/badge/skills/fagemx/prismstack/dogfood.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.00979 |
| Opus 5 | $0.00037 | $0.00490 |
| Sonnet 5 | $0.00015 | $0.00196 |
| Haiku 4.5 | $0.00007 | $0.00098 |
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 3d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dogfood: Integration Test With a Real Domain
You are a QA tester dogfooding Prismstack. You run a real domain through the full product flow and record every issue you find.
Phase 0: Pick a Test Domain
Parse $ARGUMENTS for a domain name. If not provided, suggest:
- 小型咖啡店行銷 (small coffee shop marketing) — simple, ~10 skills, fast
- 獨立遊戲開發工作流 (indie game dev workflow) — medium complexity
- 自由接案者專案管理 (freelancer project management) — diverse skill types
Ask the user to pick one or provide their own domain.
Create a temp working directory:
_DOGFOOD_DIR=$(mktemp -d)/dogfood-test
mkdir -p "$_DOGFOOD_DIR"
echo "Working in: $_DOGFOOD_DIR"
Phase 1: Run /domain-plan
Read skills/domain-plan/SKILL.md and follow its flow for the test domain.
Execute the planning phase as if you were a real user. Record:
- Did it work? Did the skill produce a complete domain plan?
- Awkward moments: Any point where the flow was confusing or required backtracking?
- Errors: Any crashes, missing files, or broken references?
- Timing: Roughly how many tool calls / how long did the phase take?
- Output quality: Is the generated plan actually useful for the domain?
Save the plan output to $_DOGFOOD_DIR/domain-plan-output/.
Phase 2: Run /domain-build
Read skills/domain-build/SKILL.md and follow its flow using the plan from Phase 1.
Build the domain stack in $_DOGFOOD_DIR/generated-stack/.
Record the same categories as Phase 1, plus:
- Skill count: Did it generate the expected number of skills?
- Skill structure: Do generated skills follow skill-craft-guide structure?
- Shared resources: Were methodology files and shared context created?
- Completeness: Can each generated skill actually be invoked?
Phase 3: Run /skill-check on the Generated Stack
Read skills/skill-check/SKILL.md and run it with --all on the generated domain stack.
Record:
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.
- 3d ago First seen · 117 lines · 75 tokens per session scan A 339c91d50c45
dogfood is a skill published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 979 once invoked, about $0.0004 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
asc-shots-pipeline
Orchestrate iOS screenshot automation with xcodebuild/simctl for build-run, AXe for UI actions, JSON settings and plan files, Koubou-based framing (asc screenshots frame), and screenshot upload (asc screenshots upload). Use when users ask for automated screenshot capture, AXe-driven simulator flows, frame composition…
playwright-best-practices
Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
benchmark
Local-only regression / benchmark skill for ui-clone-skills maintainers. Drives the standard ui-reverse-engineering pipeline against the canonical reference site (https://realfood.gov) and records AE/SSIM, iteration count, gate fail counts, and outcome to benchmark/history.csv so prompt / sub-doc / model-version drift…
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.
card-skill
Render text and evidence into polished, shareable PNG visuals with one consistent Kenny Style visual grammar. Use this skill whenever the user asks to turn words, notes, articles, quotes, arguments, stories, open-source repository or tool material, technical commands/workflows, explicit WeChat Reading…