agentgem-share

agentgem-share is a skill for Claude Code, Codex from ninemindai/agentgem. It costs 40 tokens per session (348 once invoked), scanned B, original, MIT.

Instructions for publishing a Gem based on the user's real AgentGem usage. They define a workflow that scans sessions, reviews selected ingredients, shows a privacy-filtered attestation, and publishes only after confirmation.

In plain words
What is it for?
Scanning usage, selecting skills or MCP servers to share, inspecting private ingredients, reviewing the publishable data, and signing and publishing an attestation after explicit approval.
Why use it?
They make the user review exactly what will leave the machine and keep usage counts tied to tool-generated records rather than invented claims.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ninemindai/agentgem/agentgem-share
Any agent
npx skills add ninemindai/agentgem --skill agentgem-share
Clone the repo
git clone --depth 1 https://github.com/ninemindai/agentgem

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agentgem-share

README.md
[![agentmods](https://agentmods.dev/badge/skills/ninemindai/agentgem/agentgem-share.svg)](https://agentmods.dev/skills/ninemindai/agentgem/agentgem-share)
Your own site
<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>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 348 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash 5522e157925d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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."
skills/agentgem-share/SKILL.md · 28 lines

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

  1. Ground in real usage. Call scan_workflow. If it returns no sessions, stop and say so.
  2. 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.
  3. Build + show. Call build_attestation with the selection. Render the returned willPublish list and the scrubbed envelope to the user verbatim — this is the privacy gate. Say plainly: "This is exactly what leaves your machine."
  4. Confirm, then publish. Only on explicit user confirmation, call sign_and_publish. Report the publishedRef, gemDigest, and ingestId (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.
Changes

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.

  1. 4d ago First seen · 28 lines · 40 tokens per session scan B 5522e157925d

Subscribe to this mod's changes

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.