capability provider invariants

A set of rules for keeping capability providers and their configuration consistent in a software system. It covers actor-specific card state, callback runtimes, plugin provider selection, display titles, and same-provider attachment storage.

In plain words
What is it for?
Use it when changing card state, callback providers, Cloudflare callbacks, plugin settings, display-title helpers, plugin installation, or MySQL/PostgreSQL attachment storage.
Why use it?
It prevents user-specific data from leaking into shared content and stops the system from running with mismatched or unsafe providers. It also keeps configuration and runtime behavior aligned.

Instructions file for GitHub Copilot

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 instructions/borgius/kanban-lite/capability-provider
Clone the repo
git clone --depth 1 https://github.com/borgius/kanban-lite

Made for: GitHub Copilot.

Per session 397 This file is loaded in full into every session.
When invoked 397 The same file — it is already loaded in full.
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 $0.00397 $0.00397
Opus 5 $0.00198 $0.00198
Sonnet 5 $0.00079 $0.00079
Haiku 4.5 $0.00040 $0.00040

Measured yesterday against content hash c24dfec2a621, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

capability provider invariants 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 yesterday.

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.

.github/instructions/capability-provider.instructions.md · 20 lines

What it actually says

Capability / provider invariants

  • card.state and callback.runtime are first-class capability/provider namespaces.
  • Actor-scoped card state must live outside shared card content/frontmatter.
  • Standalone transports that expose card.state must decorate cards per request/session auth context; raw shared broadcasts must not carry actor-scoped state.
  • Board-configured card display titles must use the shared display-title helper; raw markdown title extraction remains the source of truth for storage, filenames, and rename logic.
  • Callback configuration lives in shared plugin settings; plugin enablement maps to plugins[capability].provider, not a separate enabled boolean.
  • Cloudflare callback.runtime uses plugins["callback.runtime"].provider === "cloudflare" with type: "module" handlers only.
  • Enabled Cloudflare callback module-set changes are bootstrap/redeploy gated and must fail closed on runtime drift.
  • Cloudflare queue delivery is event-scoped; durable checkpoints and idempotency are tracked per handler.
  • For MySQL/PostgreSQL same-provider attachment.storage, use createMysqlAttachmentPlugin(engine) / createPostgresqlAttachmentPlugin(engine) instead of placeholder exports.
  • In-product plugin installs accept only exact unscoped kl-* package names; reject scopes, specifiers, flags, URLs, paths, and extra args.
  • Plugin-settings reads, lists, errors, and install output must reuse the shared redaction policy across SDK, API, CLI, MCP, and UI surfaces.
  • JSON Forms provider-option UIs should reuse the shared .card-jsonforms wrapper/styling hook instead of introducing a second theme.
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. yesterday First seen · 20 lines · 397 tokens per session scan A c24dfec2a621

Subscribe to this mod's changes

capability provider invariants is an instructions file published in the GitHub repository borgius/kanban-lite (7 stars, last pushed 3mo ago), licensed MIT. It adds 397 tokens to every session, about $0.0020 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens