Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/zhanlincui/agent-skills-hunter/chat-compactor)<a href="https://agentmods.dev/skills/zhanlincui/agent-skills-hunter/chat-compactor"><img src="https://agentmods.dev/badge/skills/zhanlincui/agent-skills-hunter/chat-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/zhanlincui/agent-skills-hunter/chat-compactor"><img src="https://agentmods.dev/badge/skills/zhanlincui/agent-skills-hunter/chat-compactor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00094 | $0.00827 |
| Opus 5 | $0.00047 | $0.00413 |
| Sonnet 5 | $0.00019 | $0.00165 |
| Haiku 4.5 | $0.00009 | $0.00083 |
Grade A, and why
chat-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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chat Compactor
Generate structured summaries optimized for AI agent continuity across sessions.
Why This Exists
Human-written summaries and ad-hoc AI summaries lose critical context:
- Decision rationale gets lost (why X, not Y)
- Dead ends get forgotten (agent re-tries failed approaches)
- Implicit knowledge isn't captured (file locations, naming conventions, gotchas)
- State is unclear (what's done, what's pending, what's blocked)
This skill produces agent-optimized handoff documents that prime the next session.
Output Format
Generate a markdown file with this structure:
# Session: [Brief Title]
Date: [YYYY-MM-DD]
Duration: ~[X] messages
## Context Snapshot
[1-2 sentences: What project/task, what state it's in right now]
## What Was Accomplished
- [Concrete outcome 1]
- [Concrete outcome 2]
## Key Decisions & Rationale
| Decision | Why | Alternatives Rejected |
|----------|-----|----------------------|
| [Choice] | [Reason] | [What didn't work and why] |
## Current State
- **Working**: [files/features that are functional]
- **Broken/Blocked**: [what's not working and why]
- **Modified files**: [list with brief note on changes]
## Dead Ends (Don't Retry)
- ❌ [Approach that failed] — [why it failed]
## Next Steps (Prioritized)
1. [ ] [Most important next action]
2. [ ] [Second priority]
## Environment & Gotchas
- [Any setup notes, versions, quirks discovered]
## Key Code/Commands Reference
[Only if there are non-obvious commands or snippets the next session needs]
Workflow
- Scan conversation for: decisions, outcomes, failures, file changes, blockers
- Identify the "handoff moment" — what would a fresh agent need to continue?
- Generate structured summary using format above
- Save to file:
session-[topic]-[date].mdin project root or/home/claude/sessions/
Compaction Triggers
Invoke this skill when:
- User says: "compact", "wrap up", "save session", "summarize for next time"
- Context window exceeds ~50% capacity and task is ongoing
- Before major context switches
- End of debugging/implementation session
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 · 100 lines · 94 tokens per session scan A af0083c3a06f
chat-compactor is a skill published in the GitHub repository ZhanlinCui/Agent-Skills-Hunter (186 stars, last pushed 6mo ago), licensed MIT. It adds 94 tokens to every session and 827 once invoked, about $0.0005 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
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.