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 imphillip/gbrain-openclaw --skill maintaingit clone --depth 1 https://github.com/imphillip/gbrain-openclawWrote 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/imphillip/gbrain-openclaw/maintain)<a href="https://agentmods.dev/skills/imphillip/gbrain-openclaw/maintain"><img src="https://agentmods.dev/badge/skills/imphillip/gbrain-openclaw/maintain/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/imphillip/gbrain-openclaw/maintain"><img src="https://agentmods.dev/badge/skills/imphillip/gbrain-openclaw/maintain.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 | $0.00030 | $0.00491 |
| Opus 5.5 | $0.00012 | $0.00196 |
| Sonnet 5.5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
gbrain-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 1mo 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.
What it actually says
Maintain Skill
Run these checks periodically (every few days).
Lint checks
1. Contradictions
- Compare State sections across linked pages
- Flag: Page A says "CEO of X" but Page B says "left X in 2025"
- Resolution: check timeline entries for latest evidence, update the stale page
2. Stale info
gbrain list --type person # check for pages with old compiled_truth
gbrain timeline <slug> # are there timeline entries newer than the State section?
- Flag pages where State hasn't been updated but timeline has new entries
- Rewrite compiled_truth from latest timeline evidence
3. Orphan pages
gbrain list # for each slug:
gbrain backlinks <slug> # zero inbound links = orphan
- Either add links from related pages, or flag for deletion
4. Missing cross-references
- Scan compiled_truth for mentions of known page titles that aren't linked
- "Jane mentioned Acme Corp" but no link to companies/acme-corp → add it
5. Dead links
- For each link, verify both pages still exist
- Remove links to deleted pages
6. Open thread audit
- Pages with Open Threads items older than 30 days → flag for review
- Resolved items still in Open Threads → move to timeline
7. Tag consistency
gbrain call brain_stats '{}' # check tag counts
- Flag near-duplicates: "yc-alum" vs "yc_alum" vs "yc alum"
- Normalize: lowercase, hyphens
8. Embedding freshness
gbrain embed --stale # re-embed pages updated since last embedding run
Output
Write a maintenance report:
cat report.md | gbrain put sources/maintenance-$(date +%Y-%m-%d)
Include: findings, actions taken, pages updated, issues flagged.
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.
- 1mo ago First seen · 69 lines · 30 tokens per session scan A 57c3aa6b0364
gbrain-maintain is a skill published in the GitHub repository imphillip/gbrain-openclaw (11 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 491 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
my-wiki
A skill for managing a local Markdown knowledge vault that stores captured webpages, PDFs, Office files, notes, images, folders, and ZIP files. It links preserved source material, called References, to durable topic pages, called Concepts.
vault-summarize
Use when the user asks to summarize, digest, or get an overview of a folder, project, or set of notes in their markdown vault — runs the vault's batched map-reduce recipe so note bodies stay out of the retained conversation context.
vault-workflow
Use when the user asks you to search, read, or reason about notes in their markdown vault — guides when to use which vault tool and how to chain them for good results.
kb
Set up, evolve, or operate a hraness/kb local-first Markdown knowledge base for coding-agent memory. Use when a user asks to design KB conventions or a recurring KB ritual; search or query a KB or Obsidian vault; load or recover repository context, plans, decisions, concepts, backlinks, semantic search, or Git…
manas-answer
Answer a personal-brain question through configured local Manas generation with verified citations and explicit evidence gaps.
manas-capture
Persist a user-authorized personal memory in Manas with provenance and a deduplicated write receipt.