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/paulbreuler/limps/007-knowledge-graph-integrationgit clone --depth 1 https://github.com/paulbreuler/limpsWhat 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 | $0.00000 | $0.00489 |
| Opus 5 | $0.00000 | $0.00244 |
| Sonnet 5 | $0.00000 | $0.00098 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
007-knowledge-graph-integration 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 2d 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
Agent 007: Knowledge Graph Integration
Objective
Integrate context hierarchy with Plan 0042's knowledge graph.
Tasks
-
New entity types (
src/graph/context-entities.ts)context: workspace.md, project.md, context/*.mdmemory: *.memory.md filesadr: ADR-*.md files
-
New relationship types
INHERITS_FROM: plan → workspace contextOVERRIDES: plan value overrides workspaceSUPERSEDES: ADR → older ADRREMEMBERS: agent → memory fileCONTRIBUTES_TO: agent → plan memory
-
Graph sync (
src/context/graph-sync.ts)- Sync context files to knowledge graph on change
- Update relationships when inheritance changes
- Track supersession chains in graph
-
Enhanced queries
- "What context does plan 0042 inherit?"
- "What ADRs affect agent 001?"
- "Show supersession chain for ADR-0003"
Integration Points
Plan 0042 Proactive Watch Mode:
// When context file changes, update graph
async function onContextChange(path: string) {
await reindexContextFile(path);
await updateInheritanceRelationships(path);
await detectSupersessionConflicts(path);
}
Plan 0042 Hybrid Retrieval:
// Context-aware search
const results = await hybridSearch(query, {
includeInheritedContext: true,
includeMemory: true,
filterByPlan: planId
});
Acceptance Criteria
- Context files appear as entities in knowledge graph
- Inheritance relationships queryable via graph
- Supersession chains traversable
- Memory files linked to agents
- Watch mode updates context graph
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.
- 2d ago First seen · 72 lines · 0 tokens per session scan A bd05ab32693f
007-knowledge-graph-integration is an agent published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 489 tokens. 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 agents, from other repositories
bestmode
You are an agent - please keep going until the user’s query is completely resolved, before ending your turn and yielding back to the user.
design-interaction
Interaction Designer on the Atlas bench. Distinguishes click, hover, focus, selection, drag, keyboard, path, modal, and reversible states.
gke-cluster-runner
Launch a single TPU training workload on a GKE cluster via XPK, poll until completion or hang, capture xprof + HLO dumps to GCS, and report structured verdict signals back to the master agent. Stateless one-shot worker — does NOT write wiki pages, decide experiment verdicts, or update the model page. Use for every…
planner
Autonomous plan quality reviewer using Universal Planning Framework.
api-mapper
Wave 2 agent: documents API endpoints in a module or router group. Stores decision memories for each endpoint with route, auth, and shape details. Links endpoints with DEPENDSON, LEADSTO, and PARTOF relationships.
understand
Read this company's own material and work out what it sells.