Borrowing it
Nothing to install: this file belongs to kuaizhongqiang/TencentAgentMemoryBridge. 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/kuaizhongqiang/TencentAgentMemoryBridge/main/.codebuddy/skills/agent-memory-initializer/SKILL.mdgit clone --depth 1 https://github.com/kuaizhongqiang/TencentAgentMemoryBridgeWrote 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/kuaizhongqiang/tencentagentmemorybridge/agent-memory-initializer)<a href="https://agentmods.dev/skills/kuaizhongqiang/tencentagentmemorybridge/agent-memory-initializer"><img src="https://agentmods.dev/badge/skills/kuaizhongqiang/tencentagentmemorybridge/agent-memory-initializer.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 | $0.00145 | $0.01898 |
| Opus 5 | $0.00072 | $0.00949 |
| Sonnet 5 | $0.00029 | $0.00380 |
| Haiku 4.5 | $0.00015 | $0.00190 |
Grade C, and why
agent-memory-initializer scanned grade C with 1 finding 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 7d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
If the user has a `mem-agent-keys-*.md` file or can provide a reference project, extract credentials from there. Otherwise, ask the user to provide them. How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentMemory Initializer
Overview
Initialize the Tencent AgentMemory MCP bridge (tencent-agent-memory-mcp-bridge) in any project, configuring both CodeBuddy IDE and CLI with MCP tools (recall_memory / store_memory / search_memories) and a Stop hook for automatic conversation archiving to L0 memory.
Identity vs Project (read this first — never mix them)
| Concept | Env var | Shape | Meaning | Changes per project? |
|---|---|---|---|---|
| Platform identity | AGENT_ID |
agt-xxx |
CodeBuddy's agent identity (meta-registered entity) | ❌ fixed across projects |
| Team | TEAM_ID |
team-xxx |
Team | ❌ fixed |
| User | USER_ID |
usr-xxx |
The human user | ❌ fixed |
| Project label | TASK_ID |
project name (e.g. TencentAgentMemoryBridge) |
Project-level isolation tag, free-form string | ✅ one per project |
⚠️
task_idis NEVER an identity id: do not putAGENT_ID/TEAM_ID/USER_ID/keys intoTASK_ID. mcp-bridge ≥ 0.4.0 rejectsagt-/team-/usr-/sk-prefixed task_ids with a startup error.task_idanswers "which project is this", identity answers "who am I" — different things.
Architecture
The v3 team edition uses team/agent/user triples for memory isolation, plus an optional task_id tag for project-level isolation. Each agent (claude-code, codebuddy, openclaw, deepseek-harness) has its own memory domain under the same team and user.
| Component | Path | Target |
|---|---|---|
| MCP config (CLI) | <project>/.mcp.json |
CodeBuddy CLI |
| MCP config (IDE) | <project>/.codebuddy/mcp.json |
CodeBuddy IDE |
| Hook config | <project>/.codebuddy/settings.json |
Both IDE + CLI |
| Stop hook script | <project>/scripts/stop-memory-store.mjs |
Both IDE + CLI |
Prerequisites Check
Before starting, determine if the user has credentials available. Ask for the following values if they are not already present in the project or conversation:
API_KEY— Gateway authentication key (shared across all agents)TEAM_ID— Team ID, formatteam-xxxAGENT_ID— Agent ID for CodeBuddy, formatagt-xxxUSER_ID— User ID, formatusr-xxxUSER_KEY— User-level key, formatsk-mem-...(optional, for meta queries)MEMORY_ENDPOINT— Gateway URL (default:https://memory.kuai-private.top)SERVICE_ID— Space ID (default:default)TASK_ID— OPTIONAL. Project label. Leave unset to auto-derive from the project directory name (recommended); if set, it must be a project name, never an identity id.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 157 lines · 0 tokens per session scan C 4f30c6aca958
agent-memory-initializer is a skill published in the GitHub repository kuaizhongqiang/TencentAgentMemoryBridge (0 stars, last pushed 22d ago), licensed MIT. It adds 145 tokens to every session and 1,898 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.