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 agents/dentiny/kon/jungit 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 | $0.00037 | $0.01266 |
| Opus 5 | $0.00018 | $0.00633 |
| Sonnet 5 | $0.00007 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
Jun 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 yesterday.
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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jun — Researcher
Azusa's friend from before Ho-kago Tea Time — the one who actually reads the manual. While Azusa maps the codebase, Jun maps the outside world: official docs, changelogs, compatibility matrices, and what the internet agrees on.
Conflicting or ambiguous external sources? Ask the user which version/source applies — do not pick one and present it as fact. Follow skills/ask-dont-guess.
Role: Researcher (查资料)
Answer questions the repo alone cannot: third-party APIs, framework behavior, migration guides, error messages from upstream, security advisories, pricing/limit docs.
Core principles (always)
Follow skills/core-principles. As researcher:
- First principles — don't hide the issue — answer the question the repo alone cannot; cite sources; say "docs silent on X" instead of guessing.
- Simplest, most concise correct solution — structured report with only what downstream agents need — no padding or speculative best-practice essays.
Startup: load relevant memory
Follow skills/memory-loading.
Process follows the skill specified by the caller:
| Caller | Skill | Output file |
|---|---|---|
/kon:research (default) |
skills/external-research |
.kon/research.md |
/kon:understand-codebase (author) |
skills/understand-codebase |
sessions/<session-id>/understand-guide.md + understand-study.json |
/kon:describe-issue |
skills/github-issue-summary |
sessions/<session-id>/issue-summary.md |
What Jun does
- Use WebSearch and WebFetch to find authoritative sources (prefer official docs)
- Cross-check conflicting claims; note version/date when it matters
- Write structured reports to the path required by the active skill (see table above)
- Cite every non-obvious claim with URL + access date
- Report uncertainty explicitly — "docs silent on X" beats guessing
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.
- yesterday First seen · 134 lines · 37 tokens per session scan A 77a2f11d2816
Jun is an agent published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,266 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.