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 vinilana/invokta --skill add-invokta-capabilitygit clone --depth 1 https://github.com/vinilana/invoktaWrote 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/vinilana/invokta/add-invokta-capability)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.00670 |
| Opus 5 | $0.00041 | $0.00335 |
| Sonnet 5 | $0.00016 | $0.00134 |
| Haiku 4.5 | $0.00008 | $0.00067 |
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.
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
- Read
AGENTS.md,CUSTOMIZE.md,src/engine.ts,src/capabilities/template.ts, andtest/engine.test.tscompletely. - Define the stable capability ID, title, description, input, output, access, timeout, annotations, dependency failures, and observable errors.
- Ask for an explicit decision before changing an existing ID, schema, access rule, or output contract.
Follow RED, GREEN, REFACTOR
- Add an engine-level test that invokes the literal capability ID through
engine.invokeand fails for the missing behavior. - Cover unauthenticated access and invalid input. Cover ownership, not-found, cancellation, or dependency failure when the capability can encounter it.
- Implement the smallest capability and dependency boundary that passes.
- Refactor only after the contract is executable.
Keep one engine boundary
- Define the action with
defineCapabilityand Zod input/output schemas. - Use
access: "authenticated"for user or tenant data unless the user explicitly approves a public contract. - Treat
context.principal.idas 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.tsandinvokta.mcp.json. - Keep business logic out of
src/direct.ts,src/cli.ts,src/mcp-stdio.ts, andsrc/mcp-http.ts. - Never call a capability's
runmethod directly.
Add persistence safely
- Start domain migrations after
migrations/001_oauth.sql. - Use
002_domain.sqlfor 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.
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.
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 · 64 lines · 81 tokens per session scan A 9189d8698152
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.
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.
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…
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).
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.
convex-test
Generate convex-test tests for the app's Convex functions.
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.