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 commands/higress-group/higress/applygit 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/commands/higress-group/higress/apply)<a href="https://agentmods.dev/commands/higress-group/higress/apply"><img src="https://agentmods.dev/badge/commands/higress-group/higress/apply.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 5.1 | $0.00018 | $0.01714 |
| Opus 5 | $0.00009 | $0.00857 |
| Sonnet 5 | $0.00004 | $0.00343 |
| Haiku 4.5 | $0.00002 | $0.00171 |
Grade A, and why
Issue Spec: Apply 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Spec Apply
Coordinator: select execution mode before assigning writers. If Design or TASK is selected, or the user explicitly requests an independent worker, the Coordinator MUST NOT write code on delegated or managed paths. Without managed PROCESS, exactly one real non-Coordinator worker owns the bounded implementation. With managed PROCESS, every change-bearing work package/PROCESS has one real non-Coordinator owner; distinct packages MAY use concurrent writers. Select PROCESS only for concrete managed coordination, not child use, file count, independent review, or human handoff. If Implement is selected, persist it, perform its first QUESTION pass, then finalize the plan. Author PROCESS only for managed coordination; typed planning state remains authoritative.
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.
Delegated Paths and Narrow Coordinator Path
Unmanaged delegated path: dispatch exactly one real non-Coordinator worker in the selected checkout. Managed PROCESS: dispatch one real non-Coordinator owner per change-bearing package; proven-independent packages may run concurrently. The Coordinator waits and writes no code on either path. Each worker owns package code, focused tests, exact result commit, changed paths, decisions, risks, and non-obvious line-rationale drafts. The Coordinator owns exact-commit inspection, integration, proportionate final validation, anchor validation, and provider publication.
Coordinator code is allowed only on the narrow direct-PR fast path with no selected Design/TASK and no user delegation request; file count does not select it. Unmanaged paths use ordinary Git and project tests. Do not manufacture Implement, PROCESS, workspace lifecycle, role receipt, typed rationale, evidence, or another phase artifact merely to record delegation.
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.
- 5d ago First seen · 51 lines · 18 tokens per session scan A 8ce9a73a140e
Issue Spec: Apply is a command published in the GitHub repository higress-group/higress (9,297 stars, last pushed 2d ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,714 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 commands, from other repositories
OPSX: Fast Forward
Create a change and generate all artifacts needed for implementation in one go.
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.
kimss-create-agent
Guided flow to create a Kimss agent (management-scoped API key) and send a first message via MCP or SDK.
kimss-diagnose
Triage Kimss connectivity, identity, and common API errors (whoami, agent list, credits, rate limits).
kimss-setup
Verify Kimss MCP configuration (uvx, KIMSSAPIKEY, KIMSSBASEURL) and outline a safe smoke test.