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 aAAaqwq/AGI-Super-Team --skill context-managergit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/aaaaqwq/agi-super-team/context-manager)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/context-manager"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/context-manager.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00012 | $0.01871 |
| Opus 5 | $0.00006 | $0.00936 |
| Sonnet 5 | $0.00002 | $0.00374 |
| Haiku 4.5 | $0.00001 | $0.00187 |
Grade A, and why
context-manager 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 2d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Manager Skill
- Author: Daniel Li
- Copyright © Daniel Li. All rights reserved.
AI-powered context management for OpenClaw sessions. Uses the agent itself to generate intelligent summaries, then resets the session with compressed context.
Quick Start
# List all sessions with usage stats
~/openclaw/skills/context-manager/compress.sh list
# Check status of a specific session
~/openclaw/skills/context-manager/compress.sh status agent:main:main
# Generate AI summary (read-only, safe)
~/openclaw/skills/context-manager/compress.sh summarize agent:main:main
# Compress session: generate summary, reset, inject (DESTRUCTIVE)
~/openclaw/skills/context-manager/compress.sh summarize agent:main:main --replace
When to Use
- Context usage approaching 70-80%+
- Long sessions with extensive conversation history
- Before the session becomes slow or loses coherence
- Proactively to maintain fast, focused sessions
How It Works
- AI Summarization: Sends a prompt to the agent asking it to summarize its own context
- Backup: Saves the original JSONL session file to
memory/compressed/ - Reset: Deletes the JSONL file (official reset method)
- Inject: Sends the AI-generated summary as the first message in the fresh session
- Result: Same session key, new session ID, compressed context
Key insight: The agent has full visibility into its own context, so it generates the best possible summary.
Commands
Session Commands
| Command | Description |
|---|---|
list |
List all sessions with token usage |
status [KEY] |
Show detailed status for a session |
summarize [KEY] |
Generate AI summary (read-only) |
summarize [KEY] --replace |
Summarize AND reset session with compressed context |
compress [KEY] |
Legacy grep-based extraction (not recommended) |
check [KEY] |
Check if session exceeds threshold |
check-all |
Check all sessions at once |
Configuration Commands
| Command | Description |
|---|---|
set-threshold N |
Set compression threshold (50-99%, default: 80) |
set-depth LEVEL |
Set depth: brief/balanced/comprehensive |
set-quiet-hours HH |
Set quiet hours (e.g., "23:00-07:00") |
help |
Show help and usage examples |
What ships with it
4 files 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.
- 2d ago First seen · 230 lines · 12 tokens per session scan A 2c0b645c3876
context-manager is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 1,871 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 2026-09-05.
Other skills, from other repositories
a2wave-memory
Progressively recall and maintain a2wave cross-session memory through a compact startup catalog, bounded topics, and searchable history.
optimize-learnings
Audit and curate the learnings memory namespace — the one namespace nothing re-derives, so the only one that rots. Runs moflo's mechanical audit to nominate stale, unused, and near-duplicate entries, then decides entry by entry whether to keep, retire, compress, or merge, and propagates the result to the shared…
go-start
Session startup skill. Reads platform docs, builds context, asks which project we're working on, reads project docs — and is ready to work. Also handles continuation of a stuck task by restoring context from the interrupted session. Use when: start of a new terminal session, load context, resume interrupted work.
meditate
Deliberate session retrospective — look back over what you just did, distill the durable, reusable lessons (not session trivia), and write them to the learnings memory namespace, deduped against what is already stored. Use at the END of a meaningful chunk of work to capture high-signal lessons worth keeping long-term.…
memory-team
Guided setup for sharing moflo's durable learnings through a git-tracked JSONL artifact — for a whole TEAM on one repo, OR for one person across several MACHINES (a team of one). Use when the user says "share learnings with my team", "commit our moflo memory", "sync memory across my laptop and desktop", "set up…
memory-worktree
Verify, customize, or opt out of moflo's AUTOMATIC durable-learning sharing across git worktrees / Conductor workspaces on one machine. As of the worktree-auto-sharing change this is on by default — learnings converge across a repo's worktrees with no setup. Use when the user asks "is memory shared across my…