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 darellchua2/opencode-config-template --skill openapi-contract-adherence-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote 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/darellchua2/opencode-config-template/openapi-contract-adherence-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/openapi-contract-adherence-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/openapi-contract-adherence-skill.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 13 findings, up to high
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 →
- high Tool Misuse · line 230 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 269 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 334 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 396 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium MCP Rug Pull · line 61 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 70 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 198 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium Prompt Injection · line 450 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium MCP Rug Pull · line 452 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 477 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 453 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 Prompt Injection · line 454 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- low Tool Misuse · line 198 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00052 | $0.04636 |
| Opus 5 | $0.00026 | $0.02318 |
| Sonnet 5 | $0.00010 | $0.00927 |
| Haiku 4.5 | $0.00005 | $0.00464 |
Grade A, and why
openapi-contract-adherence-skill 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 4d 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 — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
I help you detect, classify, and plan for OpenAPI spec changes across their full consumer surface:
- Validate specs — lint baseline and revision with
redocly/spectralbefore diffing - Diff with oasdiff — produce changelog and breaking-change reports in markdown + JSON
- Classify changes — map each change to severity (Breaking / Non-breaking / Additive / Cosmetic) and semver impact
- Map consumer impact — locate SDK generator configs, direct fetch/axios/httpx call sites, and generated client files
- Generate dual-format report —
CONTRACT_DIFF.md(human-readable) +CONTRACT_DIFF.json(machine-readable) - Emit PR-gate artifact — the JSON is consumable by
pr-creation-workflow-skillfor automated label selection and merge gating
When to use me
Use this skill when:
- An OpenAPI spec changed on a branch and you need to review the impact
- You want to detect breaking changes before merging
- You need a consumer-side migration plan (which files to update, which SDKs to regenerate)
- You want to classify changes for semver label selection (
major/minor/patch) - You are reviewing a PR that touches
openapi.yaml/openapi.json - You want to regenerate client SDKs after a spec change
Trigger phrases:
- "openapi diff"
- "api contract"
- "breaking change"
- "consumer update plan"
- "contract review"
- "spec changed"
- "regenerate client"
Prerequisites
Install these tools before running the workflow. Version numbers verified as of 2026-06-21.
oasdiff (primary diffing tool)
# Go binary (repo moved from tufin/oasdiff → oasdiff/oasdiff in 2024)
go install github.com/oasdiff/oasdiff@latest
# OR Homebrew
brew install oasdiff
# OR Docker fallback (no local install needed)
# Use :stable or a pinned version tag; avoid bare :latest which tracks main
# and may contain unreleased commits
docker pull tufin/oasdiff:stable
Version pinning (recommended): pin to a specific release to keep binary and Docker output schemas consistent. As of 2026-06-14, latest stable is v1.19.1.
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.
- 4d ago First seen · 505 lines · 52 tokens per session scan A 337cd8106242
openapi-contract-adherence-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 4,636 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 2026-09-03.
Other skills, from other repositories
horse-mvc-architecture
Guide for structuring corporate Horse applications using Clean MVC (Model-View-Controller) principles and decoupling HTTP layers from business logic.
horse-ssl-tls
Guide to enabling SSL/TLS, configuring HTTPS, handling certificates, and securing transport layers.
platform-apex-generate
Primary Apex authoring skill for class generation, refactoring, and review. ALWAYS ACTIVATE when the user mentions Apex, .cls, triggers, or asks to create/refactor a class (service, selector, domain, batch, queueable, schedulable, invocable, DTO, utility, interface, abstract, exception, REST resource). Use this skill…
horse-app-structure
Guide for setting up Horse applications, bootstrap program (.dpr), basic console initialization, and registering modules.
horse-multi-instance
Guidelines for instantiating and configuring independent Horse server instances (THorseInstance) running concurrently on different ports.
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.