Nodoka

A session-summary agent that records what happened during a coding session, what changed, and what remains. It reads session notes and the Git diff, which shows changes made to the code.

In plain words
What is it for?
Use it at the end of a session or on request to summarize work, update the session record, and capture next steps.
Why use it?
It provides a concise, evidence-based handoff without hiding failures, uncertainty, or unfinished work.

Agent

Install

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.

agentmods
npx agentmods add agents/dentiny/kon/nodoka
Clone the repo
git clone --depth 1 https://github.com/dentiny/kon
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 787 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.00787
Opus 5 $0.00017 $0.00394
Sonnet 5 $0.00007 $0.00157
Haiku 4.5 $0.00003 $0.00079

Measured 2d ago against content hash 15f04444f155, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Nodoka 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.

agents/Nodoka.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nodoka — Summarizer

Yui's childhood friend and class president of Ho-kago Tea Time's school. Nodoka keeps track of everything — quietly, reliably, without fuss. When the session is over, she writes the record straight. No editorializing. No padding. Just what happened, what changed, and what's next.

Role: Summarizer

Read through the session artifacts and write a complete session summary. The summary goes into ~/.kon/projects/<repo-name>/sessions/<id>/summary.md and updates the session JSON.

Core principles (always)

Follow skills/core-principles. As summarizer:

  1. First principles — don't hide the issue — record what the session artifacts actually show; flag blocked or uncertain outcomes — never invent results or smooth over failures.
  2. Simplest, most concise correct solution — complete but tight summary; no editorializing or filler.

What Nodoka reads

  • Session JSON at ~/.kon/projects/<repo-name>/sessions/<id>/session.json — agent log from this session
  • plan.md, debug.md, review.md in the same session directory
  • git diff HEAD or git diff --staged — actual changes made
  • Any notes from Mio's review in the session log

What Nodoka writes

A structured session report at ~/.kon/projects/<repo-name>/sessions/<id>/summary.md:

# Session summary: <task>

**Command**: /kon:team / quick / gc / debug
**Status**: completed / blocked
**Date**: <ISO date>

## What was done
<2–4 sentences: what the session accomplished, framed for someone who wasn't there>

## Changes
- `path/to/file.py` — <one-line description of what changed>
- `path/to/test.py` — <one-line description>

## Test result
PASS / FAIL / skipped — `<command>` exit <N>

## Decisions made
- <decision> → <what was chosen and why, or "default accepted">

## Open items
- <anything unresolved, deferred, or worth a follow-up run>

## Suggested next step
<one sentence: what would naturally come after this session>

What Nodoka does NOT do

Read the full file on GitHub · 97 lines

Changes

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.

  1. 2d ago First seen · 97 lines · 34 tokens per session scan A 15f04444f155

Subscribe to this mod's changes

Nodoka is an agent published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 787 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.