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 bhaumikmaan/claude-code-master-skills --skill context-summarizationgit clone --depth 1 https://github.com/bhaumikmaan/claude-code-master-skillsWrote 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/bhaumikmaan/claude-code-master-skills/context-summarization)<a href="https://agentmods.dev/skills/bhaumikmaan/claude-code-master-skills/context-summarization"><img src="https://agentmods.dev/badge/skills/bhaumikmaan/claude-code-master-skills/context-summarization.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 | $0.00055 | $0.00999 |
| Opus 5 | $0.00028 | $0.00500 |
| Sonnet 5 | $0.00011 | $0.00200 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
context-summarization 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Summarization
CRITICAL: Respond with TEXT ONLY. Do NOT call any tools. You already have all the context you need in the conversation. Tool calls will waste your turn.
Two-Phase Output
Always produce two blocks:
<analysis>-- Your private scratchpad. Chronologically walk through the conversation, ensuring every point is covered. This block is stripped before the summary reaches anyone.<summary>-- The structured artifact others will read. Must stand alone without the analysis.
Analysis Phase
In your <analysis> block:
- Chronologically analyze each message and section. For each, thoroughly identify:
- The user's explicit requests and intents
- Your approach to addressing them
- Key decisions, technical concepts, and code patterns
- Specific details: file names, full code snippets, function signatures, file edits
- Errors encountered and how they were fixed
- Specific user feedback, especially corrections ("do it differently")
- Double-check for technical accuracy and completeness.
Summary Schema
Your <summary> must include these sections:
1. Primary Request and Intent
Capture all of the user's explicit requests and intents in detail.
2. Key Technical Concepts
List all important technologies, frameworks, and patterns discussed.
3. Files and Code Sections
Enumerate specific files examined, modified, or created. For each:
- Why this file is important
- Summary of changes made (if any)
- Important code snippets (include them -- they survive compaction, your memory doesn't)
4. Errors and Fixes
Every error encountered, how it was fixed, and any user feedback on the fix.
5. Problem Solving
Problems solved and any ongoing troubleshooting.
6. All User Messages
List ALL non-tool-result user messages. These are critical for understanding changing intent.
7. Pending Tasks
Tasks explicitly asked for that are not yet complete.
8. Current Work
Precisely what was being worked on immediately before this summary. Include file names and code snippets.
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.
- 8d ago First seen · 104 lines · 55 tokens per session scan A 454e530f24ac
context-summarization is a skill published in the GitHub repository bhaumikmaan/claude-code-master-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 999 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
distill-feedback
A process for turning corrections you give an agent into lasting working rules. It reviews saved conversations and asks for approval before changing those rules.
contextpilot
Optimize document ordering in LLM context for better retrieval performance.
knowledge-base
Retrieves and updates project-specific prompt knowledge from comparison evidence and user feedback. Use only for prompt analysis or post-comparison learning within a Rashomon evaluation.
obsidian-vault
Create, edit, and audit notes in an Obsidian vault. Handles frontmatter properties, wikilinks, embeds, callouts, tasks, block references, tags, and Mermaid diagrams. Plugin-aware: Dataview queries and inline fields, Tasks emoji syntax, Kanban boards, Meta Bind fields, Templater templates, Bases schemas, and Canvas…
compress
Prompt-Studio memory compressor. Shrinks CLAUDE.md, todo lists, and preference files into Prompt-Studio's lean format to cut input tokens on every load. Preserves all technical substance, code, URLs, and structure. Compressed output overwrites the original; human-readable backup stored out-of-tree as FILE.original.md…
context-economy
Automatically prepare fidelity-first, bounded context when users paste text, attach files or folders, provide webpages or PDFs for Markdown conversion, continue long conversations, or supply documents containing images and complex tables. Route each input through Text, Hybrid, or Source; reduce exact or…