Borrowing it
Nothing to install: this file belongs to hoangsonww/AI-Agents-Orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hoangsonww/AI-Agents-Orchestrator/main/.claude/skills/context-graph-builder/SKILL.mdgit clone --depth 1 https://github.com/hoangsonww/AI-Agents-OrchestratorWrote 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/hoangsonww/ai-agents-orchestrator/context-graph-builder)<a href="https://agentmods.dev/skills/hoangsonww/ai-agents-orchestrator/context-graph-builder"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-agents-orchestrator/context-graph-builder/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/hoangsonww/ai-agents-orchestrator/context-graph-builder"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-agents-orchestrator/context-graph-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00882 |
| Opus 5 | $0.00000 | $0.00441 |
| Sonnet 5 | $0.00000 | $0.00176 |
| Haiku 4.5 | $0.00000 | $0.00088 |
Grade A, and why
context-graph-builder 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 9d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Graph Builder Skill
Build, maintain, and enrich the project's context graph as you work. This skill runs automatically — agents should follow these guidelines during every task execution to incrementally improve the context graph.
When to Build Context
Always update the graph when you:
- Complete a task (success or failure)
- Discover a code pattern or anti-pattern
- Make an architectural decision
- Encounter and fix an error
- Learn a user preference (coding style, framework choice, etc.)
- Modify files in the project
Build from scratch when:
- The user provides a
--projectpath for the first time - The user requests
rescanorrebuild context - The graph is empty for the active project
How to Build Context
1. Project Registration (First Use)
When a project path is provided, the system auto-scans to create:
- A
PROJECTnode (root anchor for the project graph) FILEnodes for each directoryPATTERNnodes for detected languages, frameworks, and structureDECISIONnodes for detected CI/CD, testing, and infrastructure choicesCONTAINS/RELATED_TOedges linking them all
2. Incremental Updates During Operation
After each task execution, store context:
# After completing a task
manager.store_task(
task_description="What was done",
outcome="The result",
success=True,
agents_involved=["claude", "codex"],
files_modified=["src/auth.py"],
project_id=project_id, # Scope to current project
)
# When you discover a useful pattern
manager.store_pattern(
pattern_name="Error Handling Convention",
pattern_type="convention",
description="This project uses Result types instead of exceptions",
examples=["def fetch_user(...) -> Result[User, Error]: ..."],
languages=["python"],
)
# When you encounter and fix a bug
manager.log_mistake(
error_type="import_error",
error_message="Circular import between auth and users modules",
context_description="When refactoring the auth module",
correction="Moved shared types to a common.types module",
prevention_strategy="Keep shared types in dedicated modules",
severity="medium",
)
# When an architectural decision is made
manager.store_decision(
decision_title="Use PostgreSQL over MongoDB",
decision_description="Chose relational DB for strong consistency",
rationale="ACID transactions needed for payment processing",
alternatives_considered=["MongoDB", "CockroachDB"],
)
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.
- 9d ago First seen · 130 lines · 0 tokens per session scan A c4321e5d1c85
context-graph-builder is a skill published in the GitHub repository hoangsonww/AI-Agents-Orchestrator (84 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 882 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 2026-08-30.
Other skills, from other repositories
deepnote
DeepNote knowledge base: persistent interlinked markdown wiki with ingest, query, lint, link graph and history.
AgentDB Performance Optimization
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
AgentDB Memory Patterns
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
V3 Memory Unification
Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
session-summaries
What the chat right-panel session summary shows, what it costs, and how to make a session summarize well. Load when the user asks about the session summary panel, why a summary looks wrong or empty, or how to turn it on.