gemit

A command-line assessment that reviews the last 30 days of coding-agent sessions and creates a local HTML report. It scores context discipline, process quality, and setup maturity using fixed detectors rather than an AI model.

In plain words
What is it for?
Run it to generate and view the report, then optionally review the information that would be shared publicly and publish a results card after confirmation.
Why use it?
It shows where an agent workflow is working well or needs improvement, based on recent sessions instead of memory or guesswork.

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

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 353 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00058 $0.00353
Opus 5 $0.00029 $0.00177
Sonnet 5 $0.00012 $0.00071
Haiku 4.5 $0.00006 $0.00035

Measured 3d ago against content hash fe839da75f77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/gemit/SKILL.md · 30 lines

What it actually says

gemit

Score the user's last 30 days of coding-agent steering into a local report.

Procedure

  1. 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.
  2. Relay the printed tier and the three scores to the user in one line.
  3. 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 --yes for 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.
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. 3d ago First seen · 30 lines · 58 tokens per session scan A fe839da75f77

Subscribe to this mod's changes

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.