Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/salavender/antigravity-compound-engineering-pluginnpx agentmods add skills/salavender/antigravity-compound-engineering-plugin/session-resumeWrote 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/salavender/antigravity-compound-engineering-plugin/session-resume)<a href="https://agentmods.dev/skills/salavender/antigravity-compound-engineering-plugin/session-resume"><img src="https://agentmods.dev/badge/skills/salavender/antigravity-compound-engineering-plugin/session-resume.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 | $0.00009 | $0.00428 |
| Opus 5 | $0.00005 | $0.00214 |
| Sonnet 5 | $0.00002 | $0.00086 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
session-resume 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 7d 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.
This is a copy
100% identical to session-resume — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Session Resume Skill
Helps agents quickly understand where work left off when starting a new session.
When To Use
- At the start of any new conversation
- When context seems missing
- When user asks "what were we working on?"
Instrumentation
# Log usage when using this skill
./scripts/log-skill.sh "session-resume" "manual" "$$"
Quick Resume Checklist
1. Check Active Work
# Ready todos (highest priority)
ls todos/*-ready-*.md 2>/dev/null | head -5
# In-progress plans
ls plans/*.md 2>/dev/null
# Recent solutions (for context)
ls -t docs/solutions/**/*.md 2>/dev/null | head -3
2. Check Recent Git Activity
# Recent commits
git log --oneline -5
# Uncommitted changes
git status --short
3. Summarize Context
After gathering info, summarize:
4. Check System Health
./scripts/compound-dashboard.sh
Review health grade and recommendations before starting work.
5. Final Summary
📍 Session Context:
**Active Work:**
- {X} ready todos waiting
- Plan in progress: {plan name if any}
**Recent Activity:**
- Last commit: {subject}
- {Changed files if uncommitted}
**Suggested Next Steps:**
1. {Most logical next action}
2. {Alternative}
Automatic Triggers
Consider running this skill when you see:
- User starts with "continue", "resume", "where were we"
- First message in a new session
- User seems to lack context
References
- Todos:
todos/ - Plans:
plans/ - Solutions:
docs/solutions/ - Workflows:
.agent/workflows/
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.
- 7d ago First seen · 97 lines · 9 tokens per session scan A 3c2f9523ba4b
session-resume is a skill published in the GitHub repository salavender/antigravity-compound-engineering-plugin (47 stars, last pushed 23d ago), licensed MIT. It adds 9 tokens to every session and 428 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to session-resume, differing in 0 lines, and is treated as a copy.
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.