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/joymin5655/agent/brain-ingestnpx skills add joymin5655/Agent --skill brain-ingestgit clone --depth 1 https://github.com/joymin5655/AgentWrote 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/joymin5655/agent/brain-ingest)<a href="https://agentmods.dev/skills/joymin5655/agent/brain-ingest"><img src="https://agentmods.dev/badge/skills/joymin5655/agent/brain-ingest.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 | $0.00096 | $0.01837 |
| Opus 5 | $0.00048 | $0.00919 |
| Sonnet 5 | $0.00019 | $0.00367 |
| Haiku 4.5 | $0.00010 | $0.00184 |
Grade A, and why
brain-ingest 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 5d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/brain-ingest
Goal
Move knowledge one hop along the brain's one-way flow — from noisy, untrusted
raw/ captures to curated typed atomic notes in notes/ — and, for the notes
that have earned it, one further hop into the human-curated vault. The brain is
the fast, multi-agent working layer; the vault is the reviewed SSOT. Nothing
flows backward.
raw/<ai>/*.md ──(this skill: distill + lint gate)──▶ notes/<type>/<id>.md
(quarantine, (curated, in the graph)
kind=generated) │
▼ (evergreen only)
/wiki-ingest ──▶ vault wiki/ (human SSOT)
The paths are resolved by core/brain/store.py from $AGENT_BRAIN_DIR
(default ~/.agent/brain) — this skill never hardcodes a brain or vault path.
Run everything from the harness repo root. python3 core/brain/store.py paths
prints the resolved directories.
Steps
1. Select raw candidates
List the quarantined captures and read the ones worth curating:
find "$(python3 core/brain/store.py paths | python3 -c 'import json,sys;print(json.load(sys.stdin)["raw"])')" -name '*.md'
Read each candidate. A capture is worth distilling only if it carries a durable
insight, decision, procedure, or entity — not merely "a session happened". WIP
breadcrumbs from the Stop hook with no reusable content are left in raw/ (or
deleted); they are not promoted.
2. Dedup before you write (G3)
For each candidate idea, search the existing curated notes first:
python3 core/brain/store.py search "<key terms of the idea>"
If a note already covers it, extend or refine that note (add a typed edge, a
refines/supports link, a sharper line) rather than creating a near-duplicate.
A new note is justified only when the idea is genuinely new. This is the
anti-fragmentation rule — the same fact must not live in two notes.
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.
- 5d ago First seen · 158 lines · 96 tokens per session scan A 08bea236048e
brain-ingest is a skill published in the GitHub repository joymin5655/Agent (2 stars, last pushed 3d ago), licensed MIT. It adds 96 tokens to every session and 1,837 once invoked, about $0.0005 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
memento
Memento — autonomous nervous system for AI agents. Use for memory operations, active coercion management, goal alignment checks, dependency audits, and workspace routing.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
peek
Searches memories and displays compact one-liner results, or looks up a specific memory by ID. Use for quick memory lookups, checking if a decision was recorded, resolving [mem0:id] citations, or browsing memories without full category detail.
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.