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 skills add darellchua2/opencode-config-template --skill strategic-compact-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/strategic-compact-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/strategic-compact-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/strategic-compact-skill.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.01650 |
| Opus 5 | $0.00013 | $0.00825 |
| Sonnet 5 | $0.00005 | $0.00330 |
| Haiku 4.5 | $0.00003 | $0.00165 |
Grade A, and why
strategic-compact-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 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.
How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
I analyze AI agent session context and suggest when and how to compact it efficiently:
- Context Analysis: Assess current session size, complexity, and information density
- Criticality Assessment: Identify which context is essential vs. expendable
- Compaction Strategy: Recommend what to keep, summarize, or discard
- Summary Generation: Create compact summaries that preserve actionable information
- Session Planning: Suggest optimal session breakpoints for complex multi-step tasks
When to use me
Use this skill when:
- A session is becoming long and context window is filling up
- You want to preserve important decisions before context gets too large
- You're working on a multi-step task that spans multiple interaction rounds
- An agent is struggling with context length limits
- You want to start a new session but carry forward essential information
Trigger phrases:
- "compact context"
- "summarize session"
- "reduce context"
- "what can we drop"
- "session getting long"
- "preserve key decisions"
Core Workflow
Step 1: Assess Session Context
Analyze the current session for compaction opportunities:
| Metric | What to Measure |
|---|---|
| Token estimate | Approximate context size |
| Unique topics | Number of distinct topics discussed |
| Open tasks | Incomplete items that need tracking |
| Decisions made | Architectural or design decisions |
| Files modified | What code has been changed |
| Errors resolved | Problems that were fixed and how |
Step 2: Classify Information
Categorize all session content by retention priority:
Tier 1: Must Keep (Critical)
- Current task description and acceptance criteria
- Uncommitted changes and their purpose
- Active debugging state (current hypothesis, what's been tried)
- Blockers and dependencies
- Authentication/security context
Tier 2: Should Keep (Important)
- Architecture decisions and rationale
- Key file locations and their purposes
- API contracts and data models
- Test results and coverage status
- Partial solutions with reasoning
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 · 248 lines · 25 tokens per session scan A ceed4af94554
strategic-compact-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 1,650 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
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…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.