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/gemitnpx skills add ninemindai/agentgem --skill gemitgit clone --depth 1 https://github.com/ninemindai/agentgemWhat 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 | $0.00058 | $0.00353 |
| Opus 5 | $0.00029 | $0.00177 |
| Sonnet 5 | $0.00012 | $0.00071 |
| Haiku 4.5 | $0.00006 | $0.00035 |
Grade A, and why
gemit 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 3d 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.
What it actually says
gemit
Score the user's last 30 days of coding-agent steering into a local report.
Procedure
- Run:
npx -y @ninemind/agentgem gemit- It scans local transcripts (last 30 days), scores context discipline, process quality, and setup maturity with deterministic detectors (no LLM), and writes a self-contained HTML report.
- On a TTY the report opens in the browser; otherwise open the printed
Report:path.
- Relay the printed tier and the three scores to the user in one line.
- Offer the share. If the user wants their card published, run
npx -y @ninemind/agentgem gemit --share.- It shows exactly what would ship (scores, counts, window dates — never skill/subagent names, project names, or transcripts) and asks for confirmation.
- It prints the card URL and a prefilled X share link — hand both to the user.
Rules
- All scoring lives in the CLI. Never estimate, adjust, or re-derive a score yourself.
- Don't pass
--yesfor the user — the pre-publish confirmation is theirs to answer. - Fewer than 5 substantial sessions? Relay that the sheet fills itself after a few more steered sessions; don't apologize for the tool.
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.
- 3d ago First seen · 30 lines · 58 tokens per session scan A fe839da75f77
gemit is a skill published in the GitHub repository ninemindai/agentgem (39 stars, last pushed 6d ago), licensed MIT. It adds 58 tokens to every session and 353 once invoked, about $0.0003 per session on Opus 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
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.
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale Pod runs and workers.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
mcp-builder
Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.