add-invokta-capability

add-invokta-capability is a skill for Codex from vinilana/invokta. It costs 81 tokens per session (670 once invoked), scanned A, original, MIT.

A development procedure for adding or changing capabilities in the Invokta Action Engine. A capability is a named operation that the engine exposes to callers.

In plain words
What is it for?
Adding actions, tools, domain behavior, repository operations, database schema changes, or capability IDs to Invokta.
Why use it?
It makes each operation's inputs, outputs, permissions, errors, and dependencies explicit before implementation. Tests then check the behavior through the engine boundary.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

Good fit Adding actions, tools, domain behavior, repository operations, database schema changes, or capability IDs to Invokta.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vinilana/invokta/add-invokta-capability
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.

Any agent
npx skills add vinilana/invokta --skill add-invokta-capability
Clone the repo
git clone --depth 1 https://github.com/vinilana/invokta

Made for: Codex.

Wrote 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.

agentmods badge for add-invokta-capability

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinilana/invokta/add-invokta-capability/github.svg)](https://agentmods.dev/skills/vinilana/invokta/add-invokta-capability)
Your own site
<a href="https://agentmods.dev/skills/vinilana/invokta/add-invokta-capability"><img src="https://agentmods.dev/badge/skills/vinilana/invokta/add-invokta-capability/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.

agentmods 80×15 button for add-invokta-capability

Your own site · 80×15
<a href="https://agentmods.dev/skills/vinilana/invokta/add-invokta-capability"><img src="https://agentmods.dev/badge/skills/vinilana/invokta/add-invokta-capability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 670 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00081 $0.00670
Opus 5 $0.00041 $0.00335
Sonnet 5 $0.00016 $0.00134
Haiku 4.5 $0.00008 $0.00067

Measured 9d ago against content hash 9189d8698152, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

add-invokta-capability 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.

examples/auth-self-hosted-oauth-engine/.agents/skills/add-invokta-capability/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add an Invokta Capability

Resolve the project root as three directories above this SKILL.md. Perform all relative reads and commands from that root; do not assume the caller's current working directory is the project.

Establish the contract

  1. Read AGENTS.md, CUSTOMIZE.md, src/engine.ts, src/capabilities/template.ts, and test/engine.test.ts completely.
  2. Define the stable capability ID, title, description, input, output, access, timeout, annotations, dependency failures, and observable errors.
  3. Ask for an explicit decision before changing an existing ID, schema, access rule, or output contract.

Follow RED, GREEN, REFACTOR

  1. Add an engine-level test that invokes the literal capability ID through engine.invoke and fails for the missing behavior.
  2. Cover unauthenticated access and invalid input. Cover ownership, not-found, cancellation, or dependency failure when the capability can encounter it.
  3. Implement the smallest capability and dependency boundary that passes.
  4. Refactor only after the contract is executable.

Keep one engine boundary

  • Define the action with defineCapability and Zod input/output schemas.
  • Use access: "authenticated" for user or tenant data unless the user explicitly approves a public contract.
  • Treat context.principal.id as the ownership boundary for per-user data.
  • Inject repositories, providers, clocks, and tools through engine-owned factories or closures.
  • Register the literal ID in src/engine.ts and invokta.mcp.json.
  • Keep business logic out of src/direct.ts, src/cli.ts, src/mcp-stdio.ts, and src/mcp-http.ts.
  • Never call a capability's run method directly.

Add persistence safely

  • Start domain migrations after migrations/001_oauth.sql.
  • Use 002_domain.sql for the first domain migration; inspect the existing migration list before choosing every later number.
  • Make migrations transactional and safe to rerun.
  • Add each migration filename to src/database/migrate.ts.
  • Keep every per-user query constrained by the authenticated principal.
  • Do not couple domain tables to oauth_artifacts; OAuth persistence is an authorization-server implementation detail.
  • Extend the structure that exists in the project. Do not invent repository, domain, schema, or test files before confirming they are present or needed.

Read the full file on GitHub · 64 lines

Files

What ships with it

1 file 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.

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. 9d ago First seen · 64 lines · 81 tokens per session scan A 9189d8698152

Subscribe to this mod's changes

add-invokta-capability is a skill published in the GitHub repository vinilana/invokta (128 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 670 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

server-side-calls

Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.

trpc/trpc · 61 tokens

mem0-test-integration

Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…

mem0ai/mem0 · 207 tokens

prowler-test-api

Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).

prowler-cloud/prowler · 62 tokens

python-sdk

Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.

ComposioHQ/composio · 60 tokens

convex-test

Generate convex-test tests for the app's Convex functions.

openclaw/clawhub · 16 tokens

voiden

Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.

VoidenHQ/voiden · 28 tokens