contribute-spec-fix

contribute-spec-fix is a skill for Claude Code from jentic/jentic-one. It costs 138 tokens per session (6,764 once invoked), scanned A, original, Apache-2.0.

A procedure for correcting an existing OpenAPI specification, a machine-readable description of an API.

In plain words
What is it for?
It helps create an OpenAPI Overlay, check the result with linting and repeatability tests, and submit the fix as a pull request.
Why use it?
It provides a consistent way to record and validate a specification fix before sharing it with the project community.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is [overlay stacking contract](../../docs/overlays.md) before authoring overlapping fixes..

Good fit It helps create an OpenAPI Overlay, check the result with linting and repeatability tests, and submit the fix as a pull request.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jentic/jentic-one
agentmods
npx agentmods add skills/jentic/jentic-one/contribute-spec-fix

Made for: Claude Code.

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 contribute-spec-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/jentic/jentic-one/contribute-spec-fix/github.svg)](https://agentmods.dev/skills/jentic/jentic-one/contribute-spec-fix)
Your own site
<a href="https://agentmods.dev/skills/jentic/jentic-one/contribute-spec-fix"><img src="https://agentmods.dev/badge/skills/jentic/jentic-one/contribute-spec-fix/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 contribute-spec-fix

Your own site · 80×15
<a href="https://agentmods.dev/skills/jentic/jentic-one/contribute-spec-fix"><img src="https://agentmods.dev/badge/skills/jentic/jentic-one/contribute-spec-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,764 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 warn 7 Sept 2026
SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 58
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 214
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 215
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 143
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
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 $0.00138 $0.06764
Opus 5 $0.00069 $0.03382
Sonnet 5 $0.00028 $0.01353
Haiku 4.5 $0.00014 $0.00676

Measured 10d ago against content hash 93e4b47104ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

contribute-spec-fix 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 10d 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.

skills/contribute-spec-fix/SKILL.md · 504 lines

How it starts

The opening of the file, as written. The whole thing — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contribute a Spec Fix (Overlay → PR → optional local apply)

Fix a spec in jentic-public-apis the right way: capture the fix as an OpenAPI Overlay, validate it, and open a PR so the whole community gets the fix. This is the improvement flywheel — fixes made by AI agents are contributed back, not siloed on one machine.

Target: $ARGUMENTS (a vendor/api id like posthog.com/posthog-api, or a path to a spec).

If the vendor is not in the catalog at all, this is the wrong skill — use import-new-api instead; this skill only fixes specs that already exist.

The flywheel — read this first

        broken spec found
                │
                ▼
     write overlay  ──►  validate (lint + idempotency)  ──►  apply to openapi.json
                │
                ▼
     ┌─────────────────────────────────────────────┐
     │  DEFAULT: PR to jentic/jentic-public-apis     │  ← community gets the fix
     └─────────────────────────────────────────────┘
                │
                ▼  (only if the user is blocked on maintainer approval time)
     ┌─────────────────────────────────────────────┐
     │  FALLBACK: apply the SAME overlay to the      │  ← unblocks the user now;
     │  local Jentic registry — PR stays open        │    PR is still the source of truth
     └─────────────────────────────────────────────┘
                │
                ▼  (later: the registry keeps watching upstream)
     ┌─────────────────────────────────────────────┐
     │  upstream spec changes  ──►  registry emits:  │
     │   • update_available      → re-import to adopt│  ← fix merged upstream? adopt + retire
     │   • update_conflicts_overlay → operator picks │  ← never silently overwrites the fix
     └─────────────────────────────────────────────┘

Always open the PR. The local apply is an impatience valve, not a substitute — it uses the same overlay document, so nothing forks. Never skip the PR just because a local apply worked.

Prerequisites

Read the full file on GitHub · 504 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. 10d ago First seen · 504 lines · 138 tokens per session scan A 93e4b47104ff

Subscribe to this mod's changes

contribute-spec-fix is a skill published in the GitHub repository jentic/jentic-one (175 stars, last pushed today), licensed Apache-2.0. It adds 138 tokens to every session and 6,764 once invoked, about $0.0007 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.