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 thebestmensch/dot-me --skill me-cardgit clone --depth 1 https://github.com/thebestmensch/dot-meWrote 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/thebestmensch/dot-me/me-card)<a href="https://agentmods.dev/skills/thebestmensch/dot-me/me-card"><img src="https://agentmods.dev/badge/skills/thebestmensch/dot-me/me-card/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thebestmensch/dot-me/me-card"><img src="https://agentmods.dev/badge/skills/thebestmensch/dot-me/me-card.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00076 | $0.04634 |
| Opus 5 | $0.00038 | $0.02317 |
| Sonnet 5 | $0.00015 | $0.00927 |
| Haiku 4.5 | $0.00008 | $0.00463 |
Grade A, and why
me-card 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 11d 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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
me-card
Produce one stdout-friendly ASCII card that summarizes everything saved in
~/.me/. The output is the deliverable. No prose before or after.
The card is an open-frame zine column — single vertical rail down the
left, no top/right/bottom walls. Section breaks cut across the rail. The
brand mark ·me sits at the top, a one-line signature at the bottom. Each
section uses its own glyph so the card scans by silhouette, not just text.
What to read
Best-effort. Skip any file that doesn't exist or fails to parse.
~/.me/identity.yaml— name, preferred_name, pronouns, handle, location, knows_about, work, past_work, projects, pets, inner_circle, family~/.me/preferences.yaml— tools, aesthetics (formality, color_temperature, current_theme, design_principles), media~/.me/working-style.yaml— behavioral rule groups (not rendered, but counted for the footer total)~/.me/voice.md— first non-empty heading or one-line tagline if present; optional, only used for the footer~/.me/memory/— count files by prefix:feedback_*.md,reference_*.md,project_*.md,user_*.md. Each.mdminusMEMORY.mdand.gitkeep~/.me/identity.yamlspec_version— primary source for the footer version stamp. Fall back to~/.me/plugin/.claude-plugin/plugin.jsonversiononly ifspec_versionis absent. (The stamp tracks the user's.mespec, not the plugin software version, so the data source takes precedence over the runtime source.)
Use a quick ls | wc -l style scan for the memory tallies. Don't read the
memory file contents.
Layout
Total column width: 68 chars (2 leading spaces + rail + 3-space gutter + ≤62 chars content).
Lines start with ┃ (two leading spaces, rail, three-space gutter) and
then content. Blank lines between sections are ┃ (rail only). Never close
the right side — content trails off into whitespace, that's the design.
Section glyph alphabet
Each section uses one glyph as its row marker (the column-2 character after the gutter). Pick by section:
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.
- 11d ago First seen · 359 lines · 76 tokens per session scan A 63f0f211e14d
me-card is a skill published in the GitHub repository thebestmensch/dot-me (3 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 4,634 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
audit-history
Use when reviewing past agent sessions, auditing memory health, identifying repeated corrections or friction, cleaning up stale memories, proposing new skills and rules from usage patterns, or identifying mechanical improvements (testing, linting, static analysis, tooling) that could improve outcomes.
capture-knowledge
Capture business knowledge from Slack into the Knowledge Base. Two modes: (1) Single thread: pass a Slack URL to capture one discussion (2) Sweep: scan entire channels for Q&A threads, launch parallel agents per channel, catalog all findings Use when the user says "capture this", "salva esse conhecimento", "captura…
learn
Capture a learning (bug, workaround, pattern, gotcha) and save to persistent memory. Use when the user says "learn", "save this", "remember this", "note this", "record this", "never forget this", or when a non-obvious bug fix, workaround, or integration pattern is discovered during development.
my-context-sync
A context-gathering process that collects information from several sources and combines it into one document.
llm-wiki
Use when the user references LONGMEMORY, llm-wiki, wiki-, project/session context, prior work, or asks to load context from a markdown wiki.
save-q
A skill that saves the main questions and answers from the current conversation to a question bank.