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 magic3007/dotfiles --skill insightsgit clone --depth 1 https://github.com/magic3007/dotfilesWrote 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/magic3007/dotfiles/insights)<a href="https://agentmods.dev/skills/magic3007/dotfiles/insights"><img src="https://agentmods.dev/badge/skills/magic3007/dotfiles/insights.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.00714 |
| Opus 5 | $0.00034 | $0.00357 |
| Sonnet 5 | $0.00014 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
insights 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Insights
Generate a local report from Codex JSONL sessions. Keep the workflow local: do not upload transcripts, browse for enrichment, or invoke another model process. Use the current Codex turn for the qualitative analysis.
Workflow
-
Resolve this skill directory as
${CODEX_HOME:-$HOME/.codex}/skills/insights. If that path is unavailable, use the directory containing thisSKILL.md. -
Run the collector. Unless the user requests a range or project, analyze all eligible top-level sessions:
python3 <skill-dir>/scripts/codex_insights.py collectOptional filters are
--days N,--project TEXT, and--max-sessions N. Do not add a filter merely to reduce work. -
Read the generated
analysis-input.jsoncompletely. It contains aggregate statistics and bounded, redacted session excerpts; do not reopen raw session files unless the collector reports a parsing problem. -
Create the analysis skeleton:
python3 <skill-dir>/scripts/codex_insights.py init-analysis -
Replace every placeholder in
insights.jsonwith evidence-based analysis in the user's language. Preserve the schema. -
Validate and render:
python3 <skill-dir>/scripts/codex_insights.py validate-analysis python3 <skill-dir>/scripts/codex_insights.py render -
Return the clickable absolute path to the timestamped HTML report, plus a compact at-a-glance summary. Mention the analyzed/scanned counts and any skipped or malformed sessions.
Analysis rules
- Use second person. Be candid and constructive, not flattering.
- Separate Codex-caused friction from user/environment friction.
- Treat satisfaction as inferred unless the excerpt contains an explicit user signal.
- Count only goals the user requested, not autonomous exploration performed by Codex.
- Ground examples in the supplied excerpts, but paraphrase them. Never reproduce credentials, private tokens, or long prompt passages.
- Recommend an
AGENTS.mdaddition only when the same instruction recurs in at least two distinct sessions. - Prefer practical Codex capabilities: Skills, MCP, subagents,
codex exec, plugins, hooks, and projectAGENTS.md. Verify a command with local--helpbefore putting it in copyable code if it is not already confirmed by the evidence file. - Do not mistake high tool counts for productivity. Evaluate whether the workflow reached the user's goal.
- If evidence is sparse, state that clearly and leave unsupported optional lists empty instead of inventing patterns.
What ships with it
4 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.
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.
- 2d ago First seen · 54 lines · 68 tokens per session scan A 5d7a4a681a3d
insights is a skill published in the GitHub repository magic3007/dotfiles (11 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 714 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 2026-09-06.
Other skills, from other repositories
dotfiles
Chezmoi dotfiles conventions and patterns. Use when modifying dotfiles, adding new managed files, working with chezmoi templates, or syncing agent skills and subagents through agentspec.
use-notion
Reference for using the Notion API via the notion-agent subagent. Use to expore and update Notion workspace content.
orchestrate-agents
Orchestrate multiple agent CLIs (Claude, Codex, Antigravity) via tmux with a shared fleet store, dispatching one guardian subagent per pane. Survey-first: inspects and adopts existing tmux sessions, windows, and agent panes before creating anything new. Use when running a multi-agent session, dispatching parallel…
assess-quality
Foundational quality framework: the five questions (readable, easy to start, expands without bloat, consistent, intentional) every other dev skill is judged against, plus the dual-audience and workshop principles. Use when onboarding to a project, defining a quality bar, setting an assessment checklist, or arbitrating…
create-oss-skill
Create well-formed Agent Skills following the agentskills.io specification. Scaffold directories, write SKILL.md files, bundle scripts, and structure instructions for progressive disclosure. Use when creating a new skill, reviewing skill structure, optimizing a skill description, or setting up evals for skill quality.
extend-oss-skills-to-claude
Extend standard agentskills.io skills with Claude Code-specific features. Invocation control, subagent execution, dynamic context injection, string substitutions, model/effort overrides, and deployment scoping. Use when adapting a portable skill for Claude Code, adding Claude-specific frontmatter, setting up subagent…