Higress is a cloud-native API gateway built on Istio and Envoy that routes and manages APIs and can be extended with WebAssembly plugins. It is used to manage APIs for AI models and MCP servers as well as general services, and the catalogue entries provide agent workflows and integrations for operating it.
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 agentmods add skills/higress-group/higress/issue-spec-githubnpx skills add higress-group/higress --skill issue-spec-githubgit clone --depth 1 https://github.com/higress-group/higressWrote 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/higress-group/higress/issue-spec-github)<a href="https://agentmods.dev/skills/higress-group/higress/issue-spec-github"><img src="https://agentmods.dev/badge/skills/higress-group/higress/issue-spec-github.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00030 | $0.00547 |
| Opus 5 | $0.00015 | $0.00273 |
| Sonnet 5 | $0.00006 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
issue-spec-github 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub CLI
Use the gh CLI only for GitHub operations outside issue-spec's workflow and discussion surfaces.
Use
- Inspect PR status, reviews, mergeability, CI, workflow runs, releases, labels, and repository metadata.
- Use structured --json/--jq output. Use git directly for local repository operations.
- After the code writer returns valuable line-rationale drafts, validate each stable path/symbol/changed-line anchor against the pushed exact head and confirm the rationale still applies and contains no secret, raw payload, or credential. Return invalid, stale, or sensitive drafts to the writer, or drop them with an explanation; never rewrite them while claiming worker authorship. Publish valid unchanged text as a GitHub-native inline PR comment by resolving
commit_id,path, right-sideline, andside=RIGHTafter push. Writers need no GitHub access and never guess diff positions. Publish no filler. - Before human-review handoff, publish or refresh the ordinary GitHub PR discussion headed
### Implementation Rationalethroughgh pr comment <pr> --body-file <file>and use it as the summary/index for inline rationale. If a safe inline comment cannot be created, retainpath:symbol/lineplus the writer-authored rationale in this top-level discussion. Report requested write failure and retain the body without treating any rationale comment as evidence or delivery acceptance. - Ordinary issue discussion writes: write a body file and run issue-spec comment create --repo owner/repo --issue 42 --body-file reply.md --json. The selected issue backend owns the write. Never use GitHub CLI or a raw issue-comment API write.
- issue-spec owns optional planning, implementation coordination, durable projection, PR context, and human handoff. The human and code host own current review, checks, approval, merge, and closing behavior. Do not use GitHub endpoints for non-GitHub providers.
Setup and examples
gh auth login
gh auth status
gh pr view 17 --repo owner/repo --json number,title,state,url
gh pr checks 17 --repo owner/repo
gh run view <run-id> --repo owner/repo --log-failed
gh api repos/owner/repo/labels --jq '.[].name'
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 · 33 lines · 30 tokens per session scan A 10e038e03734
issue-spec-github is a skill published in the GitHub repository higress-group/higress (9,288 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 547 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
API Gateway Testing
API gateway testing skill covering rate limiting validation, request routing, authentication proxy testing, load balancing verification, circuit breaker testing, and gateway configuration validation for Kong, Envoy, and AWS API Gateway.
kimss-mcp-setup
Configure the Kimss MCP server in Cursor, Windsurf, Claude Desktop, or other MCP clients using uvx, environment variables, and the seven v1 tools.
kimss-sdk
Integrate Kimss via dual-listener gateway (OpenAI /v1 or Anthropic /v1/messages + Agent-Id headers). Optional kimss package for control-plane register/usage only.
serverless-expert
Design and implement production-grade serverless applications with optimal performance, cost efficiency, and scalability. Use when the user mentions serverless or FaaS, AWS Lambda, Azure Functions, Cloud Functions, cold starts, event-driven architecture, or API Gateway-fronted workloads.
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
omni-mcp
Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.