Borrowing it
Nothing to install: this file belongs to the-sid-dani/second-brain-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/the-sid-dani/second-brain-os/main/.claude/skills/contact-log/SKILL.mdgit clone --depth 1 https://github.com/the-sid-dani/second-brain-osWrote 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/the-sid-dani/second-brain-os/contact-log)<a href="https://agentmods.dev/skills/the-sid-dani/second-brain-os/contact-log"><img src="https://agentmods.dev/badge/skills/the-sid-dani/second-brain-os/contact-log.svg" alt="Measured on agentmods" 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 | $0.00180 | $0.04319 |
| Opus 5 | $0.00090 | $0.02159 |
| Sonnet 5 | $0.00036 | $0.00864 |
| Haiku 4.5 | $0.00018 | $0.00432 |
Grade A, and why
contact-log 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 6d 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
contact-log
Write-mode entity-keyed mutation. Append a new interaction entry to a matched contact's ## Interaction log section, auto-bump last_interaction frontmatter. Append-only — never rewrites prior entries, never touches About / Recurring topics / Open commitments.
Before you begin: read the Configuration section in root CLAUDE.md. Path tokens like <workspace.resources> resolve from there — don't hardcode.
Why this exists
Without /contact-log, a contact file is a static address book — populated once, then frozen. The Chief-of-Staff function (track who said what when) needs interaction history to compound. Each conversation adds a line; over months that line-set becomes the answer to "what did I promise last time?" and "when did we last sync?"
/contact-log is the write counterpart to /contact (read). Together they make the contacts directory alive — entity-keyed read AND entity-keyed append, with the locked schema preserved across both.
The schema (frontmatter fields, body sections, WikiLinks pattern, status enum) is defined in <workspace.root>/<workspace.resources>/contacts/README.md — read that first if you need schema details. This skill references the schema; it does not reproduce it.
When to use
Trigger phrases (write-mode signals — broad on purpose):
- "/contact-log " / "/contact-log"
- "log my 1:1 with " / "log my meeting with " / "log my call with "
- "append interaction with " / "record my chat with "
- "I just talked to " / "just spoke with , log it" / "had a sync with "
- "wrote/promised/agreed with — log it"
The verb is the signal. Read-mode verbs ("who is", "what's my context with", "remind me about", "tell me about") fire /contact instead. Mutation verbs ("log", "append", "record", "talked-to", "spoke with") fire this skill.
Do NOT trigger for:
- Read-only recall of a person — that's
/contact. Phrases like "who is X again?", "context on Y". - Scaffolding a brand-new contact or editing other profile fields — handle as a separately approved direct edit after reading the canonical contacts README. This skill only appends interactions.
- Writing to the daily log —
/contact-logdoes NOT touchmemory/YYYY-MM-DD.md. <user.name> writes the day's narrative to memory/ separately.
What ships with it
1 file 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.
- 6d ago First seen · 268 lines · 180 tokens per session scan A c3d4b4a4503c
contact-log is a skill published in the GitHub repository the-sid-dani/second-brain-os (2 stars, last pushed 1mo ago), licensed MIT. It adds 180 tokens to every session and 4,319 once invoked, about $0.0009 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
claudeai-sync
One-command incremental sync of a claude.ai WEB account into the Obsidian vault — pull only new/changed chats, fold them in as notes (idempotent, never overwrites curated ones), extract artifacts as first-class notes, concept-link the new artifacts, refresh the RAG index + dashboard. Trigger on "/claudeai-sync", "pull…
gmail
Check / search / digest Gmail on demand across multiple mailboxes (personal / assistants / work) via the owner's own OAuth connector — no browser needed, 0 tokens for the raw pull. Trigger on "/gmail", "check mail", "any important emails", "find the email about ", "mail digest". Read-only by default; drafting/sending…
inbox
Check this machine's cross-machine mailbox — messages Claude on ANOTHER computer left for Claude here, via a file-synced bus folder (no couriers). Trigger on "/inbox", "check inbox", "messages from the other machine". Also the way to SEND a message to Claude on another machine. A session-start hook auto-shows new…
coach
A daily AI coach — a forward-looking accountability + mirror loop grounded in the owner's FULL identity layer (the vault knows them better than anyone). Trigger on "/coach", "morning review", "evening review", "what should I do today", "keep me on track". Runs a MORNING kick (mirror → accountability → one rock →…
faaa-sync
On-demand pull of FRESH follow-up call notes from a dedicated Telegram group into the CRM layer of the vault. Incremental + idempotent (dedup by Telegram message id) — safe to re-run, never makes duplicates. Manual counterpart of the weekly scheduled sync; both call the SAME scripts (single source of truth). Trigger…
chatgpt-sync
On-demand pull of FRESH ChatGPT conversations into the Obsidian vault — the manual twin of the scheduled nightly sync. Incremental + idempotent (keyed by conversationid; never clobbers concept-enriched notes, never duplicates). Both entry points call the SAME orchestrator script (single source of truth). Trigger on…