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 instructions/cdskill/qalma/agents-mdgit clone --depth 1 https://github.com/cdskill/qalmaWhat 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 | $0.01059 | $0.01059 |
| Opus 5 | $0.00530 | $0.00530 |
| Sonnet 5 | $0.00212 | $0.00212 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
qalma AGENTS.md 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qalma Repository Guidance
Mission
Build an Angular-first, headless, plugin-based rich text editor on ProseMirror. The product should offer the composability expected from modern editors such as Plate or Tiptap while feeling native to Angular.
The public developer experience is the product. Prefer typed Angular-facing contracts, signal-based state, consumer-owned UI, accessibility, and deliberate extension points over exposing raw ProseMirror details.
Repository Skills
- Use
qalma-architecturefor product vision, repository structure, public API design, new library boundaries, and architectural refactors. - Use
qalma-plugin-developmentwhenever adding, changing, reviewing, or removing an editor plugin, command, mark, node, shortcut, or ProseMirror behavior. - Use
qalma-docs-syncafter adding, changing, reviewing, or removing a public plugin capability that affectsapps/docs, docs navigation, playground behavior,libs/editor/README.md, or durable workflow guidance. - Use
git-commitwhen the user invokes/commitor asks to generate and create a conventional commit from staged changes. - Use
qalma-releasewhen discussing or changing versioning, the release scripts, the GitHub Actions release workflow, Nx release configuration, or npm publishing for@qalma/editor.
Architectural Invariants
- Keep
libs/editorheadless. Do not bake toolbar buttons, product styling, or a fixed feature set into editor primitives. - Let consumers select plugins in TypeScript and compose their UI explicitly through Angular templates and content projection.
- Treat
apps/sandboxas a real consumer and executable documentation. It must use only the intentional public API from@qalma/editor. - Keep ProseMirror as the internal engine. Expose it publicly only after an explicit API design decision.
- Let a
QalmaPlugincontribute schema nodes or marks, commands, command states, shortcuts, and ProseMirror plugins. - Expose configurable features through Qalma-owned option interfaces, immutable defaults, and validation. Do not leak a third-party options object as the public contract by default.
- Keep first-party plugins in
libs/editor/src/lib/pluginsuntil a real dependency, release, ownership, or bundle boundary justifies a dedicated lib. - Preserve unique plugin keys, schema names, command names, and shortcuts.
- Keep the public barrel intentional and small. Do not export internal ProseMirror helpers or compatibility aliases without a concrete need.
- Keep
plugins/qalmaas the public agent skill pack for Codex, Claude-compatible skill loaders, and other agents that consumeSKILL.mdfolders.
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 · 104 lines · 1,059 tokens per session scan A 9a67bfc28cb8
qalma AGENTS.md is an instructions file published in the GitHub repository cdskill/qalma (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,059 tokens to every session, about $0.0053 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 instructions, from other repositories
aifed AGENTS.md
Instructions for ImitationGameLabs/aifed, covering agents.md, directory structure, common tasks, testing aifed in .playground/ and dependency management.
aifed CLAUDE.md
Instructions for ImitationGameLabs/aifed, a project described as: A text editor designed for AI agents.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode tree-widgets.instructions.md
Use when asked to consume workbench tree widgets in VS Code.
vscode accessibility.instructions.md
Use when implementing accessibility features, ARIA labels, screen reader support, accessible help dialogs, or keybinding scoping for accessibility. Covers AccessibleContentProvider, CONTEXTACCESSIBILITYMODEENABLED, verbosity settings, and announcement patterns.
vscode writing-tests.instructions.md
VS Code test writing guidelines — unit tests, integration tests, snapshot tests, and clean teardown patterns. Reference when writing or updating tests.