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/darellchua2/opencode-config-template/context-budget-skillnpx skills add darellchua2/opencode-config-template --skill context-budget-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote 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/darellchua2/opencode-config-template/context-budget-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/context-budget-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/context-budget-skill.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 5.1 | $0.00022 | $0.02220 |
| Opus 5 | $0.00011 | $0.01110 |
| Sonnet 5 | $0.00004 | $0.00444 |
| Haiku 4.5 | $0.00002 | $0.00222 |
Grade A, and why
context-budget-skill 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.
How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
I audit the token overhead of every loaded component in an OpenCode configuration and surface actionable optimizations:
- Inventory: Scan all agents, skills, rules, and MCP servers that consume context
- Classify: Bucket each component by necessity (Always / Sometimes / Rarely needed)
- Detect Issues: Identify bloat, redundancy, and common problem patterns
- Report: Produce a structured context budget report with prioritized recommendations
When to use me
Use this skill when:
- Session performance feels sluggish or output quality is degrading
- You've recently added many skills, agents, or MCP servers
- You want to know how much context headroom you actually have
- Planning to add more components and need to know if there's room
- Before deploying configuration changes to catch bloat early
Trigger phrases:
- "audit context budget"
- "context budget"
- "token overhead"
- "how much context am I using"
- "audit config bloat"
- "check skill overhead"
Core Workflow
Step 1: Inventory
Scan all component directories and estimate token consumption.
Agents (opencode_app/.opencode/agents/*.md)
- Count files and estimate tokens per file (
words × 1.3) - Extract
descriptionfrontmatter length - Flag: files >200 lines (heavy), description >50 words (bloated frontmatter)
Skills (opencode_app/.opencode/skills/*/SKILL.md)
- Count directories and estimate tokens per SKILL.md (
words × 1.3) - Flag: files >300 lines (heavy)
- Note: skills are loaded on demand, so only description fields consume always-on context
Rules / Instructions (AGENTS.md chain)
- Path 1:
AGENTS.md(repo-level instructions) - Path 2:
deploy/.AGENTS.md(user-space deployment) - Path 3:
opencode_app/AGENTS.md(Docker mode) - Measure file size, section count
- Flag: combined total >500 lines
MCP Servers (opencode_app/opencode.json → mcpServers)
- Count configured servers
- Estimate schema overhead at ~100-200 tokens per server
- Flag: servers with >20 tools, servers that wrap simple CLI commands
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 · 255 lines · 22 tokens per session scan A 474ee04cf2ac
context-budget-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 22 tokens to every session and 2,220 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
wiki
Cross-iteration memory as a weakness graph (weakness nodes + solution cards), extracted from the deprecated evograph algorithm's run-dir format per its own maintainer note. Select via memoryskill: wiki in capevolve.yaml (default is md-files). Copied into every iteration's working dir as ./guidance/memory-wiki/ when…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…