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 winstonkoh87/Athena-Public --skill context-compactorgit clone --depth 1 https://github.com/winstonkoh87/Athena-PublicWrote 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/winstonkoh87/athena-public/context-compactor)<a href="https://agentmods.dev/skills/winstonkoh87/athena-public/context-compactor"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/context-compactor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/winstonkoh87/athena-public/context-compactor"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/context-compactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 95 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00030 | $0.00905 |
| Opus 5 | $0.00015 | $0.00452 |
| Sonnet 5 | $0.00006 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
context-compactor 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 10d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Context Compactor v2.0
Protects the session from Token Bloat and "Lost in the Middle" syndrome.
Source: Claude Code
/compactprompt architecture (2026-03-31). Key Innovation: Uses an<analysis>scratchpad block (chain-of-thought) that gets stripped before the summary reaches context. The analysis improves summary quality but consumes no tokens in the final context window.
Triggers
"compact", "token limit", "clean memory", "summarize session", "context full"
Execution Protocol
Step 1: Analysis Phase (Private Scratchpad)
Wrap your analysis in <analysis> tags. This is a drafting scratchpad that will be stripped from the final output. In your analysis:
- Chronologically analyze each message and section of the conversation. For each section thoroughly identify:
- The user's explicit requests and intents
- Your approach to addressing the user's requests
- Key decisions, technical concepts and frameworks discussed
- Specific details like: file names, full code snippets, function signatures, file edits
- Errors you ran into and how you fixed them
- Specific user feedback — especially if the user told you to do something differently
- Double-check for technical accuracy and completeness
Step 2: 9-Section Summary (Structured Output)
After analysis, produce a summary in <summary> tags with exactly these sections:
1. Primary Request and Intent
— Capture ALL explicit user requests and intents in detail
2. Key Technical Concepts
— List all important technical concepts, technologies, and frameworks discussed
3. Files and Code Sections
— Enumerate specific files examined, modified, or created
— Include full code snippets where applicable
— Include WHY each file read or edit is important
4. Errors and Fixes
— List ALL errors encountered + how fixed + user feedback on each
5. Problem Solving
— Document problems solved and ongoing troubleshooting
6. All User Messages (Non-Tool-Result)
— Verbatim list of ALL user messages
— CRITICAL for detecting intent drift across the session
7. Pending Tasks
— Outline any pending tasks explicitly asked to work on
8. Current Work
— Describe in detail precisely what was being worked on IMMEDIATELY before this summary
— Include file names and code snippets
9. Optional Next Step
— Only if directly in line with user's most recent explicit request
— Include DIRECT QUOTES from the most recent conversation
— Do NOT start on tangential or old completed requests
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.
- 10d ago First seen · 101 lines · 30 tokens per session scan A 0ccd82050653
context-compactor is a skill published in the GitHub repository winstonkoh87/Athena-Public (585 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 905 once invoked, about $0.0002 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 skills, from other repositories
imap-smtp-email
Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.
task_automation
Design effective automated workflows using scheduled tasks, prompt chaining, and delivery channels.
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
session-wrap
Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
lark-cli
Use when the user wants to operate Lark or Feishu via the local lark-cli (@larksuite/cli), including install, app credentials, OAuth, readiness checks, and safe read/write boundaries.
opencli
Use when the user wants to use websites, browser login sessions, Electron apps, or external CLIs through a local OpenCLI setup, especially when setup guidance, readiness checks, and safe task execution are needed.