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 DantesPeak85/the-council --skill switch-handoffgit clone --depth 1 https://github.com/DantesPeak85/the-councilWrote 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/dantespeak85/the-council/switch-handoff)<a href="https://agentmods.dev/skills/dantespeak85/the-council/switch-handoff"><img src="https://agentmods.dev/badge/skills/dantespeak85/the-council/switch-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/dantespeak85/the-council/switch-handoff"><img src="https://agentmods.dev/badge/skills/dantespeak85/the-council/switch-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 | $0.00153 | $0.02112 |
| Opus 5.5 | $0.00061 | $0.00845 |
| Sonnet 5.5 | $0.00031 | $0.00422 |
| Haiku 4.5 | $0.00015 | $0.00211 |
Grade A, and why
switch-handoff 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 5d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Switch handoff
Tom works across two Claude accounts on the same machine. When he switches, the new session starts with no conversation context. Anything only the old session knew (the live state, half-done work, what's waiting on him, the gotchas it learned the hard way) is lost unless it's written down. The handoff file carries that across.
Things that do not reliably carry across an account switch, so the handoff has to cover them:
- conversation context, running background tasks, subagents, Monitors and
/loops (they die with the session); - claude.ai artifacts, cloud routines/scheduled agents, connectors (they belong to an account; the other account may not open them). Copy anything essential from an artifact into the handoff;
- memory, if the two accounts use different config dirs. Write the handoff so it stands alone.
Files on disk, git, gh and the shell are machine-level and do carry across.
Modes: write (outgoing) and load (incoming). /switch-handoff write or /switch-handoff load.
Where handoffs live
<main checkout>/docs/superpowers/handoffs/YYYY-MM-DD-<topic>-handoff.md
Always write into the main checkout, never into a worktree, even when this session works inside one.
A previous handoff was written only inside .claude/worktrees/*, and the main checkout never saw it.
Find the main checkout with:
git rev-parse --path-format=absolute --git-common-dir # parent of this path = main checkout
If the project isn't a git repo, use <cwd>/docs/superpowers/handoffs/. <topic> is a short slug for
the workstream (e.g. lba-master). If a handoff for the same topic already exists today, add a
suffix (-b) and mark it as superseding the earlier one.
Write mode (before the switch)
- Find the previous handoff for this topic (same search as load step 1). The new one is a delta
on it: keep what's still true, update what changed, and say
supersedes <file>in the title line. Carry unchanged sections forward in full. Don't write "see previous". The incoming session should need one file.
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.
- 5d ago First seen · 162 lines · 0 tokens per session scan A 773eaea2c3ae
switch-handoff is a skill published in the GitHub repository DantesPeak85/the-council (3 stars, last pushed 6d ago), licensed MIT. It adds 153 tokens to every session and 2,112 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
user-thoughts
A skill that stores a user's project decisions and constraints in mdbase, a persistent project knowledge store. The records can be reused across sessions and by different coding assistants.
archive
Persistent knowledge wiki and memory system that compounds across conversations using an Obsidian-compatible vault. Consult at the START of any non-trivial task to recall project context, preferences, and past discoveries. Ingest sources and build wiki pages when accumulating knowledge on a topic. Save at the END when…
project-wiki
A system for creating and maintaining a project wiki: a set of organized documents that explain a software project's plans, rules, references, and progress.
mindos-zh
A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
mindos-max
MindOS: local knowledge assistant & global memory layer. Keeps decisions, notes, SOPs, debugging lessons, architecture choices, research findings, preferences, conversation summaries for all connected agents. PROACTIVE: (1) search MindOS first for past context, (2) offer to save after valuable work, (3) persist key…