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 strikersam/autonomous-ai-agency --skill session-handoffgit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/strikersam/autonomous-ai-agency/session-handoff)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/session-handoff"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/session-handoff/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/strikersam/autonomous-ai-agency/session-handoff"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/session-handoff.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 | $0.00032 | $0.00883 |
| Opus 5 | $0.00016 | $0.00441 |
| Sonnet 5 | $0.00006 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade B, and why
session-handoff scanned grade B with 1 finding 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 12d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/state/agent-state.json # machine state How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: session-handoff
When to Use
Use this skill when:
- Pausing mid-task and planning to resume later
- Handing off to a different AI session or developer
- A task is too large to finish in one session
- You want a clean resume point before a context window reset
This is more detailed than wrap-up — it focuses on producing a handoff artifact
that another session can use to continue without asking any questions.
Instructions
Step 1 — Capture current state
Gather the raw facts:
git status # what's staged / unstaged
git log --oneline -5 # recent commits
git stash list # any stashes
cat .claude/state/agent-state.json # machine state
tail -30 .claude/state/checkpoint.jsonl # recent steps
Step 2 — Write the handoff document
Update .claude/state/NEXT_ACTION.md with the full handoff:
# Session Handoff
**Date:** YYYY-MM-DD HH:MM
**Branch:** <current branch>
**Objective:** <one sentence — what is being built?>
---
## What Was Accomplished This Session
- <completed item 1>
- <completed item 2>
- <completed item 3>
## Current State
**Working tree:** <clean | N files modified | N staged>
**Tests:** <passing | failing — see blockers>
**Last commit:** `<hash> <message>`
## Exactly Where We Left Off
<Describe the precise stopping point. Include file name and line number if mid-edit.>
## Next Actions (in order)
1. **First:** `<exact command or action>`
2. **Then:** `<next action>`
3. **Finally:** `<last action to complete the task>`
## Blockers
- <blocker 1 — what is it and why is it blocking?>
- None (if clear)
## Key Decisions Made
- **Decision:** <what was decided> **Reason:** <why>
- <repeat for each significant decision>
## Files Changed This Session
| File | Change |
|------|--------|
| `path/to/file.py` | Added X, modified Y |
## Do Not Touch
- `<file>` — in progress, half-written
- `<module>` — requires risky-module-review before any changes
## Context for Next Session
<2–3 sentences of context that would take 10 minutes to re-derive.
Include any gotchas, unexpected behaviour, or things that will matter.>
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.
- 12d ago First seen · 139 lines · 32 tokens per session scan B 7c7d65f204ef
session-handoff is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 883 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
state-management
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
persistent-memory
Observation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.
context-management
Project context loading, isolation, and persistent state management across CCPM sessions.
memclaw
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura…