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 skills add TencentCloud/TencentDB-Agent-Memory --skill memorycoregit clone --depth 1 https://github.com/TencentCloud/TencentDB-Agent-MemoryWrote 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/tencentcloud/tencentdb-agent-memory/memorycore)<a href="https://agentmods.dev/skills/tencentcloud/tencentdb-agent-memory/memorycore"><img src="https://agentmods.dev/badge/skills/tencentcloud/tencentdb-agent-memory/memorycore/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/tencentcloud/tencentdb-agent-memory/memorycore"><img src="https://agentmods.dev/badge/skills/tencentcloud/tencentdb-agent-memory/memorycore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 121 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00070 | $0.01689 |
| Opus 5.5 | $0.00028 | $0.00676 |
| Sonnet 5.5 | $0.00014 | $0.00338 |
| Haiku 4.5 | $0.00007 | $0.00169 |
Grade A, and why
openclaw-memory-tencentdb-setup 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 1mo 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 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.
- .dockerignore 1.7 KB
- .npmignore 279 B
- bin/export-tencent-vdb.mjs 690 B runs code
- bin/migrate-sqlite-to-tcvdb.mjs 460 B runs code
- bin/read-local-memory.mjs 716 B runs code
- bin/seed-v2.mjs 1.4 KB runs code
- docker-compose.local-mongo.yaml 3.9 KB
- Dockerfile 7.9 KB
- hermes-plugin/memory/memory_tencentdb/__init__.py 37 KB runs code
- hermes-plugin/memory/memory_tencentdb/client.py 11 KB runs code
- hermes-plugin/memory/memory_tencentdb/plugin.yaml 458 B
- hermes-plugin/memory/memory_tencentdb/README.md 14 KB
- hermes-plugin/memory/memory_tencentdb/supervisor.py 17 KB runs code
- index.ts 42 KB runs code
- kubb.config.ts 993 B runs code
- openclaw-plugin/.gitignore 31 B
- openclaw-plugin/docs/architecture.md 7.0 KB
- openclaw-plugin/index.ts 10 KB runs code
- openclaw-plugin/openclaw.plugin.json 2.7 KB
- openclaw-plugin/package.json 818 B
- openclaw-plugin/README_CN.md 9.1 KB
- openclaw-plugin/README.md 9.4 KB
- openclaw-plugin/src/format.ts 3.2 KB runs code
- openclaw-plugin/src/hooks/capture.ts 8.3 KB runs code
- openclaw-plugin/src/hooks/recall.ts 1.8 KB runs code
- openclaw-plugin/src/sanitize.ts 3.5 KB runs code
- openclaw-plugin/src/tools/conversation-search.ts 1.9 KB runs code
- openclaw-plugin/src/tools/memory-search.ts 1.6 KB runs code
- openclaw-plugin/src/tools/read-cos.ts 1.3 KB runs code
- openclaw-plugin/tsconfig.json 446 B
- openclaw.plugin.json 16 KB
- package.json 6.2 KB
- pi-plugin/.gitignore 26 B
- pi-plugin/index.ts 3.4 KB runs code
- pi-plugin/package.json 664 B
- pi-plugin/README.md 3.8 KB
- pi-plugin/tsconfig.json 259 B
- pi-plugin/vitest.config.ts 162 B runs code
- pnpm-workspace.yaml 351 B
- README_CN.md 12 KB
- README.md 11 KB
- scripts/bench-checkpoint-lock.ts 6.6 KB runs code
- scripts/bench-l0-mongo/bench.ts 25 KB runs code
- scripts/bench-l0-mongo/build-compare.mjs 20 KB runs code
- scripts/bench-l0-mongo/compare-8c32g.html 32 KB
- scripts/bench-l0-mongo/generate.ts 13 KB runs code
- scripts/bench-l0-mongo/index.html 27 KB
- scripts/bench-l0-mongo/insert.ts 7.2 KB runs code
- scripts/bench-l0-mongo/merge-reports.mjs 3.5 KB runs code
- scripts/bench-l0-mongo/metrics.ts 1.8 KB runs code
- scripts/bench-l0-mongo/parse-qps-log.mjs 5.1 KB runs code
- scripts/bench-l0-mongo/probe-ceiling.ts 8.8 KB runs code
- scripts/bench-l0-mongo/probe-query-ceiling.ts 6.2 KB runs code
- scripts/bench-l0-mongo/query.ts 6.5 KB runs code
- scripts/bench-l0-mongo/report.ts 2.5 KB runs code
- scripts/bench-l0-mongo/view-report.html 12 KB
- scripts/ci/check-skill-queue-isolation.sh 5.1 KB runs code
- scripts/cleanup-vdb-test-dbs.ts 3.9 KB runs code
- scripts/db/mongodb-init.js 4.0 KB runs code
- scripts/db/sqlite-init.sql 8.1 KB
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.
- 1mo ago First seen · 201 lines · 70 tokens per session scan A 49e7c99a39f1
openclaw-memory-tencentdb-setup is a skill published in the GitHub repository TencentCloud/TencentDB-Agent-Memory (29,249 stars, last pushed yesterday), with no licence file. It adds 70 tokens to every session and 1,689 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
memory-consolidate
Consolidate L1 memory atoms into L2 scene blocks and L3 persona. Invoked by the memory-consolidator agent, or manually via /memory-consolidate.
tmem-cli
Inspect/manage the local memory store via the tmem CLI — counts, keyword/hybrid search, view persona, list/open scenes (tmem scene ), recent changes, sync vectors, thresholds, and cross-project search (tmem search --all, tmem projects). Trigger on "how many memories", "show my persona", "what scenes exist", "search…
memory-view
Open the memory visualiser in the browser — a health check on the memory store: is it working, what is wrong, and what to run to fix it. Run manually via /memory-view.
memory-seed
Extract L1 memory atoms from Claude Code conversation history. Run manually via /memory-seed.
memory-poisoning-detection
Detect persistent instruction injection or long-term memory poisoning. Focus on writing/retaining hostile instructions for future tasks, not data leakage.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…