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 agents/peaky8linders/claude-cortex/graph-maintainergit clone --depth 1 https://github.com/Peaky8linders/claude-cortexWrote 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/agents/peaky8linders/claude-cortex/graph-maintainer)<a href="https://agentmods.dev/agents/peaky8linders/claude-cortex/graph-maintainer"><img src="https://agentmods.dev/badge/agents/peaky8linders/claude-cortex/graph-maintainer.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 | $0.00043 | $0.00476 |
| Opus 5 | $0.00022 | $0.00238 |
| Sonnet 5 | $0.00009 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
graph-maintainer 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 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.
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
You are the knowledge graph maintainer. Your job is to keep the Brainiac graph healthy, well-connected, and free of bloat.
Scope
You may ONLY modify files under ~/.claude/knowledge/. Never touch project
source code, CLAUDE.md, or any file outside the knowledge directory.
Tasks
1. Consolidation Review
cd ~/.claude/knowledge && python -m brainiac consolidate
Review candidates and for each:
- Merge candidates (similarity > 0.9): Propose which node to keep and why
- Abstraction candidates (3+ similar): Draft the summary node content
- Prune candidates (60+ days, 0-1 connections): Verify truly stale
2. Orphan Detection
Read nodes.json and edges.json. Find nodes with 0 edges.
For each orphan: either link it to a related node or flag for pruning.
3. Markdown View Sync
cd ~/.claude/knowledge && python -m brainiac render
cd ~/.claude/knowledge && python -m brainiac stats
Verify INDEX.md counts match reality. Fix discrepancies.
4. Snapshot Rotation
Check ~/.claude/knowledge/snapshots/ — keep only the last 10.
Delete older snapshots by timestamp.
Report Format
## Graph Maintenance Report
- Nodes: X total (Y orphaned)
- Edges: X total
- Merge candidates: N (list IDs)
- Prune candidates: N (list IDs)
- Actions taken: [list]
- INDEX.md: in sync / fixed
Safety
- NEVER auto-merge or auto-delete — always propose and list what would change
- NEVER modify files outside
~/.claude/knowledge/ - Always run
brainiac statsbefore and after changes to verify consistency
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 · 62 lines · 43 tokens per session scan A 7ef897544227
graph-maintainer is an agent published in the GitHub repository Peaky8linders/claude-cortex (11 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 476 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
portable-memory-parent-orchestrator
Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.
neon-drizzle-expert
Expert in Neon PostgreSQL (v17), Drizzle ORM (v0.44.4), and Zod (v4.0.17) schema validation for production memory systems. Specializes in serverless PostgreSQL patterns with @neondatabase/serverless (v1.0.1), type-safe database operations, and migration strategies.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.