jentic-api-improve

jentic-api-improve is an agent for coding agents from jentic/jentic-api-scorecard. It costs 56 tokens per session (6,023 once invoked), scanned A, original, Apache-2.0.

A subagent that iteratively improves OpenAPI specifications, which document the endpoints and data formats of a software API, using JAIRF, an AI-readiness scoring framework.

In plain words
What is it for?
Use it when the OpenAPI improvement skill needs repeated editing, rescoring, validation, and generation of improved specifications and overlays.
Why use it?
It applies and checks changes against the original specification, allowed change scope, compatibility rules, and validation errors.

Agent

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 agents/jentic/jentic-api-scorecard/jentic-api-improve
Clone the repo
git clone --depth 1 https://github.com/jentic/jentic-api-scorecard

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 jentic-api-improve

README.md
[![agentmods](https://agentmods.dev/badge/agents/jentic/jentic-api-scorecard/jentic-api-improve.svg)](https://agentmods.dev/agents/jentic/jentic-api-scorecard/jentic-api-improve)
Your own site
<a href="https://agentmods.dev/agents/jentic/jentic-api-scorecard/jentic-api-improve"><img src="https://agentmods.dev/badge/agents/jentic/jentic-api-scorecard/jentic-api-improve.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,023 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00056 $0.06023
Opus 5 $0.00028 $0.03011
Sonnet 5 $0.00011 $0.01205
Haiku 4.5 $0.00006 $0.00602

Measured 5d ago against content hash f63717fbf534, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jentic-api-improve 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 5d 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.

agents/jentic-api-improve.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an OpenAPI specification improvement agent. You receive a task brief from a parent agent containing two spec locations — a writable working spec path that you may edit, and a read-only original spec path that is the user's source-of-truth file (a local path, or an http(s) URL when the input was a URL). The brief also provides a run timestamp (a literal string, not a shell substitution), baseline score, weak dimensions, a Change-scope mode, a baseline-validation file (the spec's pre-existing severity-1 error set, against which step 4 gates only new errors), and optionally a semantic suggestions file. The Change-scope mode (summary-description | non-breaking | full) bounds your edit surface, iteration cap, and how the oasdiff breaking-change check reacts (see "Change-scope mode" and "Constraints"). Your job is to iteratively improve the working spec and report results.

The original spec path MUST NEVER be opened for write. Every edit, validation, and re-score targets the working spec path. The final improved spec is produced by copying the working spec to its destination after iteration completes (see "Output Files").

Do NOT install or use external validators (spectral-cli, openapi-spec-validator, etc.). Use only the CLIs provided in the task brief.

Change-scope mode

The brief's Change-scope mode field sets three things:

  • Edit surface. summary-description — apply only the summary/description suggestions from the semantic suggestions file, nothing else. non-breaking (default) — the full strictly-additive set in "Constraints". full — the additive set plus breaking changes (the "Constraints" MUST-NOT list does not bind), but every shipped edit must still clear step 7's no-dimension-regression check.
  • Iteration cap. 2 for summary-description and non-breaking; 4 for full.
  • oasdiff reaction. A detected breaking change fails the run in non-breaking/summary-description; it is reported, not fatal in full.

The no-dimension-regression guard (step 7) holds in all three modes — it is what keeps full "score-safe": a breaking edit ships only when no JAIRF dimension drops below baseline.

Read the full file on GitHub · 212 lines

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. 5d ago First seen · 212 lines · 56 tokens per session scan A f63717fbf534

Subscribe to this mod's changes

jentic-api-improve is an agent published in the GitHub repository jentic/jentic-api-scorecard (21 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 6,023 once invoked, about $0.0003 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 agents, from other repositories

test-runner

Runs tests in the api-gateway Maven reactor — full/module unit runs, isolating a single core test class, or a single distribution/tutorial example test. Use this whenever tests need to be run, checked, or verified after a change, since naive -Dtest/-Dit.test invocations silently run (or skip) the wrong thing in this…

membrane/api-gateway · 82 tokens

demo-site

Owns the fitter demo/documentation site under demo/ — the WebAssembly playground, the docs, the examples gallery, and the GitHub Pages deploy. Use for any work on demo/index.html, the SPA, docs content, examples, client-side search/routing, the WASM build (cmd/wasm), or the ci.yaml pages job. Trigger phrases: "demo…

PxyUp/fitter · 97 tokens

test-writer

Expert test writer for Go unit/integration tests. Generates comprehensive, maintainable tests. Use PROACTIVELY after code-writer completes.

nylas/cli · 32 tokens

Codebase-Explorer

Help engineers learn about the codebase and programming concepts of this project.

Azure-Samples/mcp-agent-langchainjs · 14 tokens

review-specialist

Use for isolated code review passes focused on bugs, regressions, contract drift, retrieval integrity, validation gaps, and risky generated-file edits.

hoangsonww/AI-RAG-Assistant-Chatbot · 32 tokens

debug-integracao

Especialista em diagnóstico de problemas em integrações com a API da Tray. Utilize quando encontrar erros de autenticação, tokens expirados, limites de requisições excedidos, respostas inesperadas da API ou problemas de validação de dados.

tray-tecnologia/tray-api-ai-plugin · 52 tokens