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 skills/mehdic/bazinga/context-assemblernpx skills add mehdic/bazinga --skill context-assemblergit clone --depth 1 https://github.com/mehdic/bazingaWhat 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 | $0.00045 | $0.11258 |
| Opus 5 | $0.00023 | $0.05629 |
| Sonnet 5 | $0.00009 | $0.02252 |
| Haiku 4.5 | $0.00005 | $0.01126 |
Grade A, and why
context-assembler scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run(cmd_args, capture_output=True, text=True) How it starts
The opening of the file, as written. The whole thing — 1,254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context-Assembler Skill
You are the context-assembler skill. When invoked, you assemble relevant context packages for agent spawns, prioritizing by relevance and respecting token budgets.
When to Invoke This Skill
Invoke this skill when:
- Orchestrator prepares to spawn an agent and needs relevant context
- Any agent mentions "assemble context", "get context packages", or "context-assembler"
- Preparing developer/QA/tech lead spawns with session context
- Need to check for relevant error patterns before agent spawn
Do NOT invoke when:
- No active orchestration session exists
- Manually reading specific files (use Read tool directly)
- Working outside BAZINGA orchestration
Your Task
When invoked, execute these steps in order:
Step 1: Determine Context Parameters
Extract from the calling request or infer from conversation:
session_id: Current orchestration session (REQUIRED)group_id: Task group being processed (OPTIONAL - use empty string "" if not provided)agent_type: Target agent - developer/senior_software_engineer/qa_expert/tech_lead/investigator (REQUIRED)model: Model being used - haiku/sonnet/opus or full model ID (OPTIONAL, for token budgeting)current_tokens: Current token usage in conversation (OPTIONAL, for zone detection)iteration: Current iteration number (optional, default 0)include_reasoning: Whether to include prior agent reasoning for handoff (OPTIONAL)- DEFAULT BEHAVIOR: Automatically
truewhen reasoning context is beneficial:qa_expert,tech_lead: ALWAYS (handoff recipients)senior_software_engineer: ALWAYS (escalation needs prior context)investigator: ALWAYS (debugging needs full context)developer: Wheniteration > 0(retry needs prior reasoning; first attempt has none)
- Explicitly set to
falseto disable reasoning for any agent
- DEFAULT BEHAVIOR: Automatically
reasoning_level: Level of detail for reasoning retrieval (OPTIONAL)minimal: 400 tokens - key decisions onlymedium: 800 tokens - decisions + approach (DEFAULT)full: 1200 tokens - complete reasoning chain
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 1,254 lines · 45 tokens per session scan A 11dff8923d56
context-assembler is a skill published in the GitHub repository mehdic/bazinga (21 stars, last pushed 7mo ago), licensed MIT. It adds 45 tokens to every session and 11,258 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.