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 joey-barbier/ClaudeCode-Plugin --skill horka-openclaw-session-compactgit clone --depth 1 https://github.com/joey-barbier/ClaudeCode-PluginWrote 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/joey-barbier/claudecode-plugin/horka-openclaw-session-compact)<a href="https://agentmods.dev/skills/joey-barbier/claudecode-plugin/horka-openclaw-session-compact"><img src="https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/horka-openclaw-session-compact/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/joey-barbier/claudecode-plugin/horka-openclaw-session-compact"><img src="https://agentmods.dev/badge/skills/joey-barbier/claudecode-plugin/horka-openclaw-session-compact.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 | $0.00055 | $0.00744 |
| Opus 5 | $0.00028 | $0.00372 |
| Sonnet 5 | $0.00011 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
horka-openclaw-session-compact 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 9d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Compactor
Compress large OpenClaw/Claude session files to prevent context overflow while preserving key learnings.
Scope
Compresses OpenClaw session files only. Does NOT:
- Modify memory files (only reads for dedup)
- Delete original sessions without archiving first
- Process non-OpenClaw files
When to Use
- Session files exceed 20MB
- Context usage approaching limits (>60%)
- Before gateway restarts to preserve learnings
- Scheduled maintenance (cron)
Process
1. Scan for large sessions
ls -lhS ~/.openclaw/agents/main/sessions/*.jsonl
Identify files above threshold (default: 20MB).
If no sessions above threshold: "No sessions above threshold. Nothing to compact." and stop.
2. Extract meaningful messages
IGNORE: HEARTBEAT messages, messages <30 chars, system messages (GatewayRestart, Exec completed), raw command outputs.
KEEP: Decisions made, configurations performed, problems resolved + solutions, explicit learnings, project state changes.
Example of meaningful vs noise:
- Noise:
{"type":"heartbeat","ts":"..."}-- skip - Meaningful:
"Decided to use PostgreSQL over SQLite because we need concurrent writes"-- keep
3. Generate summary (max 100 lines)
## Session Compacted [START_DATE -> END_DATE]
### Configurations
- [Config]: details
### Decisions
- [Decision 1]
### Learnings
- [Problem] -> [Solution]
### Projects
- [Project]: [progress]
4. Archive and clear
- Save summary to
~/.openclaw/memory/YYYY-MM-DD.md - Compress original:
gzip -c session.jsonl > archive/session-TIMESTAMP.jsonl.gz - Clear session file to minimal size:
head -1 session.jsonl > session.jsonl.tmp && mv session.jsonl.tmp session.jsonl
Archives go to ~/.openclaw/agents/main/archive/ (NEVER in sessions/).
5. Cleanup
Move .bak and .deleted files from sessions/ to archive/.
Shell Script
Run the included session-compactor.sh for automated processing:
./session-compactor.sh # Standard run
./session-compactor.sh --dry-run # Preview changes
./session-compactor.sh --threshold-mb 30 # Custom threshold
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.
- 9d ago First seen · 105 lines · 55 tokens per session scan A 865ceda5f543
horka-openclaw-session-compact is a skill published in the GitHub repository joey-barbier/ClaudeCode-Plugin (22 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 744 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 2026-08-30.
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.