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 agents/cantara/kcp-harness/continuegit clone --depth 1 https://github.com/Cantara/kcp-harnessWhat 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 | $0.00000 | $0.00204 |
| Opus 5 | $0.00000 | $0.00102 |
| Sonnet 5 | $0.00000 | $0.00041 |
| Haiku 4.5 | $0.00000 | $0.00020 |
Grade A, and why
continue 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 yesterday.
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.
What it actually says
Continue
Continue loads MCP servers from YAML files in the .continue/mcpServers/ directory.
Setup
kcp-harness integrate continue
This generates:
.continue/mcpServers/kcp-harness.yaml
name: KCP Compliance Harness
version: 0.1.0
schema: v1
mcpServers:
- name: kcp-harness
command: npx
args:
- "kcp-harness"
- "serve"
Place this file in your project's .continue/mcpServers/ directory and restart Continue. It will auto-discover the kcp-harness server.
Notes
- Continue uses YAML format (not JSON) for directory-based MCP server configs
- Use Agent mode to access kcp-harness tools (
kcp_plan,kcp_load, etc.) - No separate rules file is needed — governance is enforced by the harness proxy regardless
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.
- yesterday First seen · 34 lines · 0 tokens per session scan A f5bdf938868e
continue is an agent published in the GitHub repository Cantara/kcp-harness (0 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 204 tokens. 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 agents, from other repositories
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
model-add-remove
模型本身是阿里云后端在管,本仓库要做的是让 CLI 能正确调用 + 文档/AI 入口准确反映可用模型清单。.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…