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/smixs/agent-second-brain/autographnpx skills add smixs/agent-second-brain --skill autographgit clone --depth 1 https://github.com/smixs/agent-second-brainWrote 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/smixs/agent-second-brain/autograph)<a href="https://agentmods.dev/skills/smixs/agent-second-brain/autograph"><img src="https://agentmods.dev/badge/skills/smixs/agent-second-brain/autograph.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 | $0.00089 | $0.03708 |
| Opus 5 | $0.00044 | $0.01854 |
| Sonnet 5 | $0.00018 | $0.00742 |
| Haiku 4.5 | $0.00009 | $0.00371 |
Grade A, and why
autograph scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
No hardcoded domains, types, or paths. The agent discovers structure from data, builds a schema, then enforces it. All scripts share `common.py`. Zero external dependencies (stdlib only, API calls via urllib). How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autograph — typed vault engine
One schema. One graph. Works on any vault.
Overview
No hardcoded domains, types, or paths. The agent discovers structure from data, builds a schema, then enforces it. All scripts share common.py. Zero external dependencies (stdlib only, API calls via urllib).
Quick Reference: 5 Workflows
| Workflow | When to use | Entry point |
|---|---|---|
| BOOTSTRAP | New vault / after import / first setup | discover.py → enforce.py → graph.py health |
| HEALTH | Daily maintenance / on request | graph.py health → fix → moc → decay |
| CREATE | New knowledge card | Schema lookup → write file → link → touch |
| SEARCH & LINK | Find info + strengthen connections | Hub → links → target; graph.py orphans → connect |
| ORCHESTRATE | Automated multi-agent workflows (no API keys) | orchestrate.py health|bootstrap |
Workflow 1: BOOTSTRAP (raw vault → structured graph)
When to use: New vault, bulk import, first setup. Run once, then switch to HEALTH.
Full guide: references/bootstrap-workflow.md
Summary (10 phases)
- Discover:
uv run scripts/discover.py <vault-dir> --verbose > /tmp/discovery.json - Generate schema: Script baseline (
generate_schema.py) + agent swarm (swarm_prepare.py→ Wave 1 haiku →swarm_reduce.py→ Wave 2 sonnet). NEVER skip the swarm. - Review: Human approves schema. Never auto-apply.
- Bootstrap + Enforce:
engine.py init+enforce.py --apply - Link cleanup:
link_cleanup.py --apply(before enrichment) - Tag enrich:
enrich.py tags --apply(via OpenRouter API) - Deduplicate:
dedup.py --apply(before link enrichment) - Link enrich:
enrich.py swarm-links --apply(always swarm-links, never links) - MOC generation:
moc.py generate - Verify:
graph.py health+enforce.py→ target 90+/100
Critical Rules
- Always run Phase 2B (agent swarm). Script alone cannot classify unstructured content.
- Always use
swarm-links, notlinks(0.3% vs 81.6% match rate). - Always dry-run first — run without
--applybefore applying. - Dedup before link enrich — prevents links to merged/trashed files.
What ships with it
21 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.
- evals/evals.json 1.5 KB
- references/bootstrap-workflow.md 12 KB
- references/card-templates.md 1.7 KB
- references/schema-reference.md 3.7 KB
- schema.example.json 2.2 KB
- scripts/common.py 18 KB runs code
- scripts/daily.py 9.9 KB runs code
- scripts/dedup.py 25 KB runs code
- scripts/discover.py 5.0 KB runs code
- scripts/enforce.py 8.5 KB runs code
- scripts/engine.py 10 KB runs code
- scripts/enrich.py 29 KB runs code
- scripts/generate_schema.py 7.2 KB runs code
- scripts/graph.py 15 KB runs code
- scripts/link_cleanup.py 5.1 KB runs code
- scripts/moc.py 6.8 KB runs code
- scripts/orchestrate.py 16 KB runs code
- scripts/research.py 11 KB runs code
- scripts/swarm_prepare.py 8.6 KB runs code
- scripts/swarm_reduce.py 11 KB runs code
- tests/test_autograph.py 74 KB runs code
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.
- 4d ago First seen · 336 lines · 89 tokens per session scan A f4649e200322
autograph is a skill published in the GitHub repository smixs/agent-second-brain (362 stars, last pushed 29d ago), licensed MIT. It adds 89 tokens to every session and 3,708 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
memory-processor
Iva's daily-memory processor. Reads the day's two-sided transcript (daily/YYYY-MM-DD.md), distills noteworthy entities / decisions / ideas into typed autograph cards, links them into the graph, and produces a daily-summary card (topics + MOC) that navigates down to the raw transcript and up to the week. Model-agnostic…
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
braindb
Memory recall and save. Use at every conversation start and whenever the user shares personal information, expertise, project context, preferences, or decisions worth remembering long-term.
braindb-agent
Persistent memory across sessions via the BrainDB agent. Use at conversation start and whenever you need to recall what you know about the user or save new information to long-term memory.
remnic-memory-workflow
Shared memory workflow for Claude Code agents connected to Remnic — recall before acting, observe during work, remember at the end. Trigger phrases include "what do you remember about", "save this for later", "any context from last time".