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/lookatitude/guild/principlesnpx skills add lookatitude/guild --skill principlesgit clone --depth 1 https://github.com/lookatitude/guildWhat 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 | $0.00223 | $0.01178 |
| Opus 5 | $0.00112 | $0.00589 |
| Sonnet 5 | $0.00045 | $0.00236 |
| Haiku 4.5 | $0.00022 | $0.00118 |
Grade A, and why
guild-principles 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 2d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
guild:principles
Implements the Karpathy 4 + Guild evidence rule, with per-group adaptations for engineering, writing, and commercial specialists.
These five lines are the system-prompt preamble for every Guild specialist — code and non-code. The skill body is the role-adapted detail: how each principle cashes out in an engineering, writing, or commercial context.
1. Think before doing
State assumptions, surface ambiguity, present tradeoffs before you act. If two interpretations of a request are both plausible, ask — don't guess.
- Code context: "Two interpretations of this API contract. Which do you want?" Name the forks before you pick one.
- Non-code context: "Is this blog post for existing users or acquisition? The angle differs." Audience and intent come before draft one.
2. Simplicity first
Ship the minimum artifact that meets the goal. No speculative scope, no scaffolding for features nobody asked for.
- Code context: 50 lines over 200 when 50 suffice. Skip the framework, skip the abstraction layer, skip the config flag for a use case that doesn't exist yet.
- Non-code context: One crisp tweet over a 15-post thread. One headline over five. The simplest form that lands the point wins.
3. Surgical changes
Every word, every line must trace to the request. Match the existing style. No drive-by edits.
- Code context: No drive-by refactors; don't delete orphan code unasked; don't rewrite adjacent functions because you'd structure them differently.
- Non-code context: Don't rewrite adjacent paragraphs the user didn't ask about. If the brand voice is terse, stay terse — don't slip into your own register.
4. Goal-driven execution
Define verifiable success criteria up front. Loop until they're met. "Done" is measurable, not a vibe.
- Code context: TDD — failing test first, then minimal code to green, then refactor. The test is the success criterion.
- Non-code context: Campaign brief says "20% CTR increase within 2 weeks" — not "improve the campaign." Without a number, there is no goal.
What ships with it
1 file 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.
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.
- 2d ago First seen · 66 lines · 223 tokens per session scan A 8bb7c9fcad07
guild-principles is a skill published in the GitHub repository lookatitude/guild (7 stars, last pushed 2d ago), licensed MIT. It adds 223 tokens to every session and 1,178 once invoked, about $0.0011 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…