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/scalenpx skills add partikularwaters/Banka --skill scalegit clone --depth 1 https://github.com/partikularwaters/BankaWhat 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 | $0.00059 | $0.01854 |
| Opus 5 | $0.00030 | $0.00927 |
| Sonnet 5 | $0.00012 | $0.00371 |
| Haiku 4.5 | $0.00006 | $0.00185 |
Grade A, and why
scale 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL: Do not execute a promotion unless the user explicitly requested this command, OR one of the current tier's thresholds is actually met (see below). Always promote exactly one tier at a time — even if it looks like both tiers' thresholds are already met, promote to the next tier up, confirm it's correct, then separately re-check whether a second promotion is also warranted. Never jump from Minimal straight to Standard in one pass.
Note: this skill's "promotion" is tier-level (Minimal→Core→Standard) only.
Protocol §2.9 defines a separate, within-tier "promotion check" — moving a
durable fact from session-state to its owning file — that remember and
moor perform directly. It is not a tier promotion and this skill has no
role in it.
Context Contract
Required: the current tier's complete state (the Banka-owned AGENTS.md
block, or every /core/ or /context/ file) · the relevant threshold
figures (word/character counts, registry entry count).
Excluded by default: the next tier beyond the one promotion step being performed — scale never previews a Core→Standard split while executing Minimal→Core.
Outputs: the proposed destination files in full, and the proposed
replacement AGENTS.md block, shown before anything is finalized.
Write authority: the marked AGENTS.md block, plus the tier's target
directory and files — only after the user confirms the shown mapping, and
only for the single tier step being promoted. A promoted project must still
pass the Cold Agent Test (Protocol §3.1) once the write completes.
Resolve Banka state first
Before reading or writing 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.
- 2d ago First seen · 132 lines · 59 tokens per session scan A 963e67190af9
scale is a skill published in the GitHub repository partikularwaters/Banka (3 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 1,854 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
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.
max
Cleans up and improves existing code without changing behavior.
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via accact(runtime="outcome").