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 nemock/company-brain --skill maintaingit clone --depth 1 https://github.com/nemock/company-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/nemock/company-brain/maintain)<a href="https://agentmods.dev/skills/nemock/company-brain/maintain"><img src="https://agentmods.dev/badge/skills/nemock/company-brain/maintain.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 | $0.00173 | $0.02661 |
| Opus 5 | $0.00086 | $0.01331 |
| Sonnet 5 | $0.00035 | $0.00532 |
| Haiku 4.5 | $0.00017 | $0.00266 |
Grade A, and why
maintain 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 7d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maintain
This skill keeps a vault healthy as it grows. Where validate reports issues, maintain fixes the ones that can be fixed without a human call — and surfaces the rest for you to address via intake or hand-editing.
You do not invent edges. You do not silently rewrite confidence away from the original. You do not flip controlled_document from true to false. Every change has a defined repair rule.
Before any maintenance
- Confirm the vault path. Default: current working directory. Refuse if
_system/PROFILE.mdis missing. - Run
cb validate --path <vault>first. Get a baseline. Note which errors are repair-eligible (filename-id, missing inverse, missing controlled_document) and which need human input (duplicate ids, unknown types, broken edge targets, missing required fields). - Run
cb maintain audit --path <vault>. Read-only preview of whatrepairanddecaywould do. Use this to set expectations with the user before writing anything.
Capabilities
Auto-repair (cb maintain repair)
Fixes three classes of issue:
- Filename-id mismatch. A node whose file is named
pillar-foo.mdbut whose frontmatter id ispillar-bargets renamed topillar-bar.md. Skipped if the target name already exists (won't clobber). - Missing inverse edges. The schema declares one inverse pair:
preceded_by↔followed_by. When A haspreceded_by: Bbut B has nofollowed_by: A, the inverse is auto-added withnote: "auto-added inverse of preceded_by from <A>". Other edge types have no declared inverse — maintain does not invent one. - Missing
controlled_document: falseon risk/IFU nodes. Nodes underrisk/orentities/indications-for-use/carry an affirmativecontrolled_document: false. When the field is absent,maintainsets it to false. When the field is present (even if true),maintainleaves it alone — the boundary is a safety rail and never gets silently flipped.
Always regenerates _system/INDEX.md at the end of the pass. Idempotent — re-running on an already-repaired vault is a no-op (modulo the INDEX.md rewrite).
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.
- 7d ago First seen · 148 lines · 173 tokens per session scan A 162b9fb62de7
maintain is a skill published in the GitHub repository nemock/company-brain (5 stars, last pushed 3mo ago), licensed MIT. It adds 173 tokens to every session and 2,661 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
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
mykg
Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs…
swarmvault
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and…
engraph
Index and search document collections using hybrid semantic + graph + full-text search. Use when users need to search knowledge bases, find connections between documents, discover related content via link graphs, or query indexed markdown collections.
compiler
Scans knowledge/, analyzes documents, generates summaries/concepts/connections to wiki/ with reference graph. Updates existing articles instead of creating duplicates.
linker
Discovers missing cross-domain connections between knowledge documents and creates/updates connection wiki articles.