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 agentmods add commands/themrgu/ai-agent-context-passoff/loadgit clone --depth 1 https://github.com/TheMrGU/Ai-Agent-Context-PassoffWrote 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/commands/themrgu/ai-agent-context-passoff/load)<a href="https://agentmods.dev/commands/themrgu/ai-agent-context-passoff/load"><img src="https://agentmods.dev/badge/commands/themrgu/ai-agent-context-passoff/load.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 | $0.00017 | $0.00359 |
| Opus 5 | $0.00009 | $0.00179 |
| Sonnet 5 | $0.00003 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
load 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 3d 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.
What it actually says
Passoff Load
Load prior handoff context using the configured passoff_* MCP tools.
Preflight
- Confirm the passoff MCP tools are available in this session.
- Inspect any inline argument after the slash command.
- If the argument looks like a handoff id, load that id.
- If no specific id is provided, load the latest handoff.
Plan
- Determine whether to load by
idorlatest: true. - Call
passoff_load. - Summarize the loaded handoff into actionable context for the current session.
Commands
- If the user supplied a likely handoff id such as
ph_..., callpassoff_loadwith thatid. - Otherwise call
passoff_loadwithlatest: true.
After loading:
- Present the title, status, timestamps, and project if returned.
- Summarize
Current State,Decisions Made,Open Questions, andNext Steps. - Treat the loaded handoff as working context for follow-up requests.
Verification
- Confirm the tool call succeeded.
- If no handoff is found, state that explicitly.
- Confirm which handoff id was loaded.
Summary
- Report the loaded handoff id
- Report whether it was loaded by explicit id or by latest
- Report the highest-signal next actions pulled from the handoff
Next Steps
- Ask the user what they want to do with the loaded context only if the next action is not already obvious.
- Otherwise continue directly with the requested work using the loaded handoff as context.
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.
- 3d ago First seen · 49 lines · 17 tokens per session scan A ad98d1673bce
load is a command published in the GitHub repository TheMrGU/Ai-Agent-Context-Passoff (0 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 359 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 2026-08-31.
Other commands, from other repositories
save-session-learnings
Document session learnings to CLAUDE.md and AGENTS.md. Use after completing significant tasks, debugging sessions, or discovering project patterns.
kiro-steering-custom
Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
wiki-synthesize
Synthesize wiki/sources/ .md pages from raw session transcripts using the configured LLM backend.
review-code
Read ALL memory bank code rules + best practices, check the files that changed, and APPLY fixes so they adhere. The active counterpart to /scan (which is read-only). Use after an AI session, before commit, to make changed files compliant.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.