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/dentiny/kon/core-principlesnpx skills add dentiny/kon --skill core-principlesgit clone --depth 1 https://github.com/dentiny/konWhat 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 | $0.00048 | $0.00576 |
| Opus 5 | $0.00024 | $0.00288 |
| Sonnet 5 | $0.00010 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
core-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 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Principles
Owner: all agents + orchestrator
Consumers: every agent, every skill, every /kon:* stage (explore, research, plan, design, debug, implement, review, gc, summarize)
These two principles rank above conventions, completeness, clever architecture, and "how we always do it."
1. Think from first principles — don't hide the issue
- Restate the actual problem in plain language before choosing an approach.
- Every decision, step, and changed line must trace back to that problem — or it is inherited complexity / cargo-cult.
- Don't hide the issue: unclear intent, missing evidence, or unverified claims → ask or stop — never assume, paper over, or defer with "we'll fix it later."
- Follow
skills/ask-dont-guess.
2. Simplest, most concise correct solution
- Among all ways that correctly solve the problem, choose the one with the fewest moving parts.
- Minimum that satisfies acceptance criteria — not a generalized version "for later."
- When trade-offs are close, simplicity wins. Reject layers, abstractions, and defensive bloat unless a concrete requirement demands them.
By stage
| Stage | First principles | Simplicity |
|---|---|---|
| Explore / research | Report what is provable; unknown stays unknown | Report only what downstream needs — no encyclopedic dumps |
| Plan / design | Restate problem; use ## Decisions needed instead of inventing scope |
Default tie-breaker: fewer files, fewer steps, flat over layered |
| Implement | Code only what the step requires | Smallest correct diff |
| Review | Default BLOCKED until the change proves it solves the real problem | Block complexity without first-principles justification |
| GC / cleanup | Remove only verified dead weight | Simplify without changing behavior |
| Summarize | Record what happened — no invented outcomes | Concise; no padding |
Related skills
- Unclear? Ask:
skills/ask-dont-guess - Plan stress-test:
skills/design-debate - Review checklist:
skills/strict-review(item 1: simplest correct implementation) - Team pipeline:
skills/teammate-flow
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 · 43 lines · 48 tokens per session scan A 314c2b16f1d4
core-principles is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 576 once invoked, about $0.0002 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…