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 dentiny/kon --skill repo-skillgit clone --depth 1 https://github.com/dentiny/konWrote 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/dentiny/kon/repo-skill)<a href="https://agentmods.dev/skills/dentiny/kon/repo-skill"><img src="https://agentmods.dev/badge/skills/dentiny/kon/repo-skill.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 5.1 | $0.00050 | $0.00846 |
| Opus 5 | $0.00025 | $0.00423 |
| Sonnet 5 | $0.00010 | $0.00169 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
repo-skill 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 8d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Skill
Owner: user (writes the files) + all agents (read them)
Consumers: every agent, via skills/memory-loading step 0
What it is
A directory of skill files you write for a specific repo. Unlike memory entries (which are key-value facts agents accumulate over sessions), repo skills are your words, loaded verbatim before any work begins.
Each skill is a named subdirectory with a SKILL.md entry point and optional sibling files. Use as many or as few skills as you want — start with one and split later.
Use repo skills to capture things that are always true about this codebase:
- Language, build system, test runner, style guide
- Maintainer and review expectations
- Architectural invariants agents must not violate
- Conventions that differ from defaults in
~/.kon/public/memory/ - Known footguns or constraints
Path
~/.kon/projects/<repo-name>/skills/
├── build/
│ └── SKILL.md ← build commands, flags, test runner
├── conventions/
│ ├── SKILL.md ← coding style, naming, patterns
│ └── examples.md ← optional sibling files within a skill
└── architecture/
└── SKILL.md ← component layout, invariants
Example: ~/.kon/projects/duckdb/skills/build/SKILL.md
Resolve paths:
python3 $KON_ROOT/hooks/_kon_paths.py project-skills-dir # → .../skills/
python3 $KON_ROOT/hooks/_kon_paths.py project-skill-files # → all skills/*/SKILL.md, sorted
Format
Plain markdown. No frontmatter required. Write what you'd tell a new engineer on their first day.
Example skills/build/SKILL.md:
# DuckDB — build
**Language**: C++17. All new code must compile clean with `-Wall -Werror`.
**Build**: `make reldebug` — always prefix with `CMAKE_BUILD_PARALLEL_LEVEL=10`.
**Test runner**: `make test`. No mocking — use real DuckDB instances.
Example skills/conventions/SKILL.md:
# DuckDB — conventions
**Maintainer**: Mark. Prefers small incremental PRs; address every comment directly.
**Architectural invariants**:
- Never acquire new locks inside the WAL write path.
- All new catalog entries must go through `CatalogTransaction`.
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.
- 8d ago First seen · 94 lines · 50 tokens per session scan A a0e9127fc73a
repo-skill is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 846 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…