linis

linis is a skill for Claude Code, Codex from partikularwaters/Banka. It costs 42 tokens per session (2,140 once invoked), scanned A, original, MIT.

A cleanup guide for files after a completed milestone. It removes temporary storytelling and outdated notes while keeping history, source information, compatibility details, and important reasoning.

In plain words
What is it for?
Use it to tidy code comments, documentation, and project context files after a release or milestone. It does not change how the code works and is not meant for files still being actively developed.
Why use it?
Finished files often contain notes that helped during development but make later work harder to understand. This keeps the useful project context while reducing that leftover clutter.

Skill for Claude CodeCodex

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 skills/partikularwaters/banka/linis
Any agent
npx skills add partikularwaters/Banka --skill linis
Clone the repo
git clone --depth 1 https://github.com/partikularwaters/Banka

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for linis

README.md
[![agentmods](https://agentmods.dev/badge/skills/partikularwaters/banka/linis.svg)](https://agentmods.dev/skills/partikularwaters/banka/linis)
Your own site
<a href="https://agentmods.dev/skills/partikularwaters/banka/linis"><img src="https://agentmods.dev/badge/skills/partikularwaters/banka/linis.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,140 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 $0.00042 $0.02140
Opus 5 $0.00021 $0.01070
Sonnet 5 $0.00008 $0.00428
Haiku 4.5 $0.00004 $0.00214

Measured 4d ago against content hash d11daa752f0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

linis 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 4d 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.

skills-kit/linis/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Linis — Filipino for "clean." Code and context files accumulate the residue of how they were built: a name here, a date there, a line quoting what someone said mid-session, a comment narrating an experiment instead of stating its settled result. None of that is wrong to have during a build — some of it is exactly what remember and the session-state file (the Minimal Banka block in AGENTS.md, core/progress.md, or context/progress-tracker.md, depending on tier) are supposed to capture while work is active. But once a version ships or a milestone closes, that residue stops being useful context and starts being clutter a future session has to read past to find what actually matters.

This skill does not touch correctness — it never changes what code does. It only changes how it's described.

Context Contract

Required: files changed in the current completed milestone, resolved from the session-state file and the version-control diff.

Conditional: a repo-wide scope, only if the user explicitly requests it · a narrower user-specified scope, respected in place of the default.

Excluded by default: files still under active work — this skill never runs against unsettled code, by design, regardless of requested scope.

Outputs: every proposed cleanup, listed for approval before any file is touched.

Write authority: only the confirmed settled file(s) in scope, and only narrative/descriptive content — operational history, provenance, compatibility facts, and load-bearing rationale are preserved, never removed.


Step 0 — Determine scope

Default: files changed in the current completed milestone, resolved from the session-state file and version-control diff. Do not expand this to a repo-wide cleanup unless the user explicitly requests that scope. If the user specifies a narrower scope, respect it.

Before reading project state, inspect AGENTS.md, the complete contents of CLAUDE.md, /core/, /context/, and the required tier files. Active schema 2 requires one complete Banka block in AGENTS.md containing these exact comments exactly once and in this order: <!-- BANKA:START -->, <!-- BANKA:STATE-SCHEMA: 2 -->, exactly one of <!-- BANKA:TIER: Minimal -->, <!-- BANKA:TIER: Core -->, or <!-- BANKA:TIER: Standard -->, then <!-- BANKA:END -->. The declared tier must match the filesystem shape and required files. CLAUDE.md must be exactly @AGENTS.md; if it is missing, schema 2 is still active for a runtime that discovers AGENTS.md directly, but report that Claude Code compatibility is unavailable.

Read the full file on GitHub · 146 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. 4d ago First seen · 146 lines · 42 tokens per session scan A d11daa752f0b

Subscribe to this mod's changes

linis is a skill published in the GitHub repository partikularwaters/Banka (3 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 2,140 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.