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 skills add cdskill/qalma --skill qalma-architecturegit clone --depth 1 https://github.com/cdskill/qalmaWrote 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/cdskill/qalma/qalma-architecture)<a href="https://agentmods.dev/skills/cdskill/qalma/qalma-architecture"><img src="https://agentmods.dev/badge/skills/cdskill/qalma/qalma-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cdskill/qalma/qalma-architecture"><img src="https://agentmods.dev/badge/skills/cdskill/qalma/qalma-architecture.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.00478 |
| Opus 5 | $0.00028 | $0.00239 |
| Sonnet 5 | $0.00011 | $0.00096 |
| Haiku 4.5 | $0.00006 | $0.00048 |
Grade A, and why
qalma-architecture 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 9d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qalma Architecture
Protect the product direction while evolving the repository from its current small foundation. Base decisions on the code that exists today and introduce boundaries only when they solve a demonstrated problem.
Start With Context
- Read product-vision.md for positioning, product principles, anti-goals, and roadmap.
- Read current-architecture.md before deciding where code belongs or changing a public contract.
- Inspect the relevant source files. Treat the references as durable intent, not a substitute for current repository state.
Make An Architecture Decision
- Classify the capability as core runtime, first-party plugin, Angular UI primitive, consumer UI, or tooling.
- Preserve the headless composition model and the ProseMirror abstraction boundary.
- Design the smallest coherent Angular-facing public API first.
- Keep implementation-specific helpers private unless consumers need them.
- Place the capability in the current
editorlibrary unless a concrete split criterion fromcurrent-architecture.mdis met. - Explain the chosen boundary, rejected alternatives, tradeoffs, and the condition that would justify revisiting it.
- Implement only the current evolutionary step when implementation is requested. Do not scaffold a speculative final monorepo.
- Update the relevant architecture reference when the implemented decision changes durable repository intent or current structure.
Preserve These Properties
- Angular-native and signal-first developer experience.
- Headless core with consumer-owned templates and styling.
- Typed, composable, independently selectable plugins.
- Stable Qalma contracts over raw ProseMirror contracts.
- Accessible behavior and observable command state.
- Small intentional public API and low mandatory bundle cost.
- Sandbox as executable consumer documentation.
Coordinate With Plugin Work
Use qalma-plugin-development when an architectural decision becomes a
plugin implementation. Return here if that plugin requires a new extension
point, public contract, or library boundary.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 53 lines · 56 tokens per session scan A ae71a1993cb9
qalma-architecture is a skill published in the GitHub repository cdskill/qalma (10 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 478 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
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
update-skills
Create or update repository skills and instructions when major learnings are discovered during a session. Use when the user says "learn!", when a significant pattern or pitfall is identified, or when reusable domain knowledge should be captured for future sessions.
sync
Sync the current session branch with its upstream branch, or publish the current session branch to a remote. Use when the user asks to sync a branch, pull latest changes, rebase onto upstream, push current branch, publish branch, or set upstream.
generate-run-commands
Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.
create-skill
Create a reusable skill (SKILL.md) that packages a workflow.
add-component
Add a new visualization component to Unovis end to end — the TypeScript core, the shared registry, the generated framework wrappers, a dev example, a gallery example, and docs. Use when asked to add/create a new component, chart type, plot, or diagram to the library, or to wire an existing core component through to…