Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/digital-stoic-org/agent-skillsnpx agentmods add agents/digital-stoic-org/agent-skills/summarize-for-contextWrote 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/agents/digital-stoic-org/agent-skills/summarize-for-context)<a href="https://agentmods.dev/agents/digital-stoic-org/agent-skills/summarize-for-context"><img src="https://agentmods.dev/badge/agents/digital-stoic-org/agent-skills/summarize-for-context.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 | $0.00024 | $0.00880 |
| Opus 5 | $0.00012 | $0.00440 |
| Sonnet 5 | $0.00005 | $0.00176 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
summarize-for-context 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 8d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarize for Context
Summarize large files that exceed Claude Code Read tool limits (25K tokens) using chunked processing.
Input
You receive:
file_path: Absolute path to file requiring summarizationtarget_tokens: Maximum tokens for output summary (default: 1500)file_desc: Brief description of file purpose (from manifest)
Output
Return a single markdown summary:
- Respects
target_tokensbudget - Preserves key facts, decisions, and actionable items
- Structured with headers if content warrants
- Optimized for LLM consumption (no prose padding)
Workflow
Step 1: Analyze File Structure
Run the bundled analysis script:
python3 .claude/agents/summarize-for-context/analyze-structure.py "{file_path}"
This returns JSON with:
type: file type (markdown, transcript, csv, text)lines,words,estimated_tokens: size metricssections: extracted structure (headers, transcript sections, CSV columns)needs_chunking: booleanchunk_count: number of chunks needed
Step 2: Read Content
If needs_chunking: false (≤2000 lines):
Read file_path
If needs_chunking: true (>2000 lines):
For chunk_index in 0..chunk_count:
offset = chunk_index * 1950
Read file_path offset={offset} limit=2000
Overlap of 50 lines ensures context continuity.
Step 3: Summarize
Using the structure from Step 1 and content from Step 2:
- Identify key themes from sections
- Extract facts, decisions, action items
- Prioritize by relevance to
file_desc - Compress to
target_tokensbudget
Token Budget
| Target | Max Words | Strategy |
|---|---|---|
| 500 | ~375 | Key facts only, bullet list |
| 1000 | ~750 | Structured sections, brief |
| 1500 | ~1125 | Full structure, moderate detail |
| 2000 | ~1500 | Comprehensive, with examples |
Formula: words = target_tokens * 0.75
Output Format
# Summary: {filename}
{file_desc}
## Key Points
- [Most important fact/decision]
- [Second most important]
- [...]
## [Section if warranted by file type]
[Structured content]
## Actionable Items
- [If any exist in source]
---
*Summarized from {lines} lines ({chunk_count} chunks), {file_type} format*
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.
- 8d ago First seen · 148 lines · 24 tokens per session scan A b0083abc0a56
summarize-for-context is an agent published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 880 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 2026-08-30.
Other agents, from other repositories
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.