Skip to content
cccskills
FreePublished on GitHub

abi-plugin-system

Review ABI's 16 compiled-in plugin fixtures, manifest validation, manual bundled registry, and real CLI/MCP run dispatch without claiming dynamic loading.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19 stars(GitHub 19 + cccskills 0)

Run score Not tested

See how to install

Files included (1)

  • SKILL.md2.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

ABI plugin system

Use this skill for the compiled Rust plugin fixtures under crates/abi-plugins/plugins/. ABI does not provide an /abi-plugin-system command, dynamic marketplace installation, sandboxing, or hot reload.

Real public paths

./tools/cargo.sh build -p abi-cli
./target/debug/abi plugin list
./target/debug/abi plugin run example-plugin "test input"

MCP exposes the frozen plugin_list and plugin_run tools. The CLI listing is alphabetical while MCP preserves bundled declaration order; their renderings and metadata shapes intentionally differ even though both dispatch through the same compiled plugin substrate.

There are no public validate, generate, or info plugin subcommands. Manifest/parity validation runs through tests and the repository driver:

.agents/skills/plugin-runtime-tester/plugins.sh
./tools/cargo.sh test -p abi-plugins

Compiled registry

  • crates/abi-plugins/src/lib.rs contains the manually maintained BUNDLED declarations and registry descriptors.
  • Each plugin directory contains abi-plugin.json, mod.rs, and stub.rs.
  • Tests check the declarations against manifests and module/stub parity.
  • A manifest target_feature is descriptive metadata, not a dynamic Cargo gate enforced by plugin run.
  • entry_point validation rejects unsafe paths and requires a relative .rs entry beneath the plugin directory.

The current fixtures are accelerator-plugin, ai-plugin, example-plugin, example-wdbx-plugin, foundationmodels-plugin, gpu-plugin, hash-plugin, metrics-plugin, mlir-plugin, mobile-plugin, nn-plugin, os-control-plugin, sea-plugin, shader-plugin, telemetry-exporter, and tui-plugin.

Manifest commands and context providers

Manifest commands[] and context_providers[] are descriptors reachable through internal __cmd__:<name> and __context__:<name> plugin-manager dispatch. They are not automatically registered as slash commands or injected contexts in abi agent tui.

Validation boundary

  • Registry presence does not prove execution; run all 16 fixtures plus an unknown-plugin negative through the runtime driver.
  • Compiled-in Rust modules are not sandboxed third-party extensions.
  • Do not claim generated registry state, symmetric CLI/MCP rendering, dynamic feature enforcement, or hot loading.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Maintain the Abbey / Aviva / Abi Discord system prompts in the Rust abbey-bot (`src/ask.rs`) and keep the hosted Grok bots (Grok Bot Abbey, Aviva Grok) in step with them. Use when the user says "improve grok bots", "abbey prompt", "persona prompt", "ask.rs", "system prompt", "tip floor", asks to change how Abbey/Aviva/Abi speak on Discord, or after an abbey-bot PR merges and the hosted bot's tip floor needs bumping. Runs as /abbey-system-prompt.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

Validate ABI docs and external collateral against repo evidence and docs/contracts/external-claims-audit.mdx. Use when auditing claims, scanning docs for unsupported QPS/sharding/FHE/AES language, checking one claim before publish, or re-confirming the external-claims audit. Agent procedure only — not a CLI or slash command. Pair with abi-doc-claims-sync when editing docs.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

Synchronize ABI Markdown and docs claims with executable behavior. Use before editing README, AGENTS.md, CLAUDE.md, GEMINI.md, docs/**/*.mdx, walkthroughs, changelogs, or any old ABI Markdown that mentions WDBX, MCP, GPU, clustering, compression, FHE, agents, or benchmarks.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

Plan and execute ABI repo work from the TODO board, roadmap/spec docs, stable Rust 1.99.1 constraints, and validation gates. Use when the user asks to find ABI todos/roadmaps, organize a large implementation from tasks/todo.md, or decide the next safe work slice. Distinct from the goals skill — that skill owns the persistent ledger tasks/goals.md; this skill plans from the active board and north-star specs.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

Validate ABI MCP JSON-RPC stdio and its custom loopback HTTP compatibility endpoint, including auth, limits, notifications, and shutdown.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

Coordinate ABI codebase health, skill telemetry, bundled-plugin runtime checks, ABI Mega inventories, stable Rust 1.99.1 gates, and cross-CLI skill synchronization. Use for full ABI health reviews and claim-honest skill/plugin improvement cycles.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

See all skills by donaldfilimon

Report a problem with this skill