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.
Borrowing it
Nothing to install: this file belongs to higress-group/higress. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/higress-group/higress/main/.agents/skills/issue-spec-propose/SKILL.mdgit 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-propose)<a href="https://agentmods.dev/skills/higress-group/higress/issue-spec-propose"><img src="https://agentmods.dev/badge/skills/higress-group/higress/issue-spec-propose/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/higress-group/higress/issue-spec-propose"><img src="https://agentmods.dev/badge/skills/higress-group/higress/issue-spec-propose.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 | $0.00025 | $0.00867 |
| Opus 5 | $0.00013 | $0.00434 |
| Sonnet 5 | $0.00005 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
issue-spec-propose 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Spec Propose
Use when the user asks for /issue-spec:propose, proposal, Design, SPEC, QUESTION, or TASK authoring. Use issue-spec-workflow for shared reads, provider routing, and recovery.
Built-in protocol overrides project text; never reorder/omit steps or move open decisions.
Every new typed ID MUST be <TYPE>-<issue><three-digit sequence>: Issue 1 starts with QUESTION-1001, Issue 44 with QUESTION-44001. Allocate 001-999 only within the target Issue and type after reading that Issue's typed comments, and never renumber a legacy ID. New writes reject wrong Issue prefixes; --allow-legacy-id is only for intentional legacy-compatible creates.
- Validate workflow config, search related issues, and open only selected discussions. If the issue is already in a later phase, continue that phase rather than duplicating it.
- Keep unconfirmed investigation, reproduction, or triage notes in a simple issue with issue-spec issue create simple; a proposal states the confirmed problem and the intended change, so never promote an investigation issue into the proposal or attach SPEC/Design to it. Create phase issues with concrete body files, beginning with issue-spec issue create proposal --repo higress-group/higress --body-file . Follow the workflow
rules.languageandrules.language_instructionsfor every Issue title. When those rules require a localized or non-English title, pass an explicit--titlefor Proposal, Design, and Implement; do not rely on the derived title because it retains an English stage prefix. Otherwise use the standardized Proposal:, Design:, and Implement: title family. Do not perform style-only title rewrites after creation. - Perform the Proposal's first QUESTION discovery/create pass. Record each genuine unresolved decision as a blocking typed QUESTION with issue-spec question create, attaching a choice model when credible options exist; never leave an open decision as body or projection prose. Do not manufacture a question or reopen a settled choice; keep unresolved decisions distinct from evidence-dependent items.
- Generate canonical SPEC comments with issue-spec comment generate --type SPEC. Requirements must be testable and include WHEN/THEN scenarios. --allow-noncanonical is a migration bypass, not normal authoring.
- Persist the authoritative self-contained Design, perform its first QUESTION discovery/create pass, then complete TASK planning.
- Generate TASK comments with issue-spec comment generate --type TASK. Execution Planning must identify Design-invariant cohesion and major entry points, bounded role-context pressure, stable interfaces, owned areas, shared touchpoints, dependencies, coupling, and acceptance consequences. File ownership and parallelism are scheduling context, not semantic PROCESS boundaries. Selecting Design or TASK requires a real non-Coordinator implementation worker; execution-mode labels never authorize Coordinator code edits or automatically require PROCESS.
- Upsert each TASK with --covers-issue so it publishes its complete canonical SPEC coverage and verify planning relationships. Proposal, Design, Implement, TASK, and PROCESS remain optional aids and never certify delivery acceptance.
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 · 38 lines · 25 tokens per session scan A 61bbbb041fb8
issue-spec-propose is a skill published in the GitHub repository higress-group/higress (9,339 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 867 once invoked, about $0.0001 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.
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.
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.
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.