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/partikularwaters/banka/linisnpx skills add partikularwaters/Banka --skill linisgit clone --depth 1 https://github.com/partikularwaters/BankaWrote 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/partikularwaters/banka/linis)<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>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 | $0.00042 | $0.02140 |
| Opus 5 | $0.00021 | $0.01070 |
| Sonnet 5 | $0.00008 | $0.00428 |
| Haiku 4.5 | $0.00004 | $0.00214 |
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.
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.
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.
- 4d ago First seen · 146 lines · 42 tokens per session scan A d11daa752f0b
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.
Other skills, from other repositories
excalidraw
Create, inspect, and edit Excalidraw diagrams as editable .excalidraw JSON files. Use when Codex needs to turn architecture sketches, process flows, user journeys, system diagrams, workshop notes, whiteboard-style visuals, or Mermaid-like node-and-edge specs into an Excalidraw file; modify existing Excalidraw scenes…
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
aria
Designs the data model, API contracts, and structural foundation of the system.
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via accact(runtime="outcome").
github-pr-description
Generate and create pull request descriptions automatically using GitHub CLI. Use when the user asks to create a PR, generate a PR description, make a pull request, or submit changes for review. Analyzes git diff and commit history to create comprehensive, meaningful PR descriptions that explain what changed, why it…