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 skills/ninemindai/agentgem/agentgem-sharenpx skills add ninemindai/agentgem --skill agentgem-sharegit clone --depth 1 https://github.com/ninemindai/agentgemWrote 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/ninemindai/agentgem/agentgem-share)<a href="https://agentmods.dev/skills/ninemindai/agentgem/agentgem-share"><img src="https://agentmods.dev/badge/skills/ninemindai/agentgem/agentgem-share.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 | $0.00040 | $0.00348 |
| Opus 5 | $0.00020 | $0.00174 |
| Sonnet 5 | $0.00008 | $0.00070 |
| Haiku 4.5 | $0.00004 | $0.00035 |
Grade B, and why
agentgem-share scanned grade B 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 4d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- This is **signed self-reported telemetry**, not proof of a real run. Never tell the user their attestation is "verified." What it actually says
agentgem-share
Publish a signed, scan-grounded usage attestation for a Gem. The numbers are computed by the MCP tools (deterministic); your job is judgment + the privacy gate.
Procedure
- Ground in real usage. Call
scan_workflow. If it returns no sessions, stop and say so. - Pick what to share. Call
inspect_ingredients. Propose 1–N candidate Gems to the user (which skills/MCPs to bundle). Let the user choose. You decide scope, never the counts. - Build + show. Call
build_attestationwith the selection. Render the returnedwillPublishlist and the scrubbed envelope to the user verbatim — this is the privacy gate. Say plainly: "This is exactly what leaves your machine." - Confirm, then publish. Only on explicit user confirmation, call
sign_and_publish. Report thepublishedRef,gemDigest, andingestId(or that ingest was skipped).
Honesty rules
- This is signed self-reported telemetry, not proof of a real run. Never tell the user their attestation is "verified."
- Private MCP servers/skills appear as salted hashes, excluded from public aggregates.
- If the user edits counts or asks to inflate usage, refuse: counts are derived, not authored.
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.
- 4d ago First seen · 28 lines · 40 tokens per session scan B 5522e157925d
agentgem-share is a skill published in the GitHub repository ninemindai/agentgem (39 stars, last pushed 7d ago), licensed MIT. It adds 40 tokens to every session and 348 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hermes-claude-bridge
Delegate complex coding tasks from Hermes to Claude Code CLI — persistent contextual sessions, real-time SSE events, model selection, human-in-the-loop, MCP server, native Hermes plugin and one-command setup.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
agy-delegate
Delegate a coding task to the Google Antigravity CLI (agy) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through agy", or "use…