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.
git clone --depth 1 https://github.com/thepushkarp/handoffWrote 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/thepushkarp/handoff/create)<a href="https://agentmods.dev/commands/thepushkarp/handoff/create"><img src="https://agentmods.dev/badge/commands/thepushkarp/handoff/create/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/commands/thepushkarp/handoff/create"><img src="https://agentmods.dev/badge/commands/thepushkarp/handoff/create.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 | $0.00012 | $0.00688 |
| Opus 5.5 | $0.00005 | $0.00275 |
| Sonnet 5.5 | $0.00002 | $0.00138 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
create 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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a comprehensive handoff document to preserve context for future Claude sessions.
Steps
-
Analyze Session Context Review the current conversation and gather:
- Current Task State: What is currently being worked on? What's in progress?
- Key Decisions: Important architectural or implementation choices made and their rationale
- Modified Files: Files that were changed during this session (check git log and git status if available, or recall from conversation)
- Blockers/Open Questions: Anything unresolved or blocking progress
- Next Steps: Clear, actionable items for the next session to continue
- Critical Context: Gotchas, edge cases discovered, important patterns, or anything the next session absolutely needs to know
- Model Summary: 8–12 bullets capturing the most important state/decisions/blockers
- Handoff Context: 10–20 lines of concrete “paste into next session” instructions (where to start, what to run, constraints)
-
Check Git Log and Status (if in a git repo) Run
git log --oneline --decorate --all --graphandgit statusto identify modified files. -
Read Existing Handoff (if any) Try to read docs/handoff/HANDOFF.md to check if it exists. If it does, you'll append to it.
-
Create Directory and Append Handoff Ensure docs/handoff/ directory exists with
mkdir -p docs/handoff, then append a new timestamped entry to docs/handoff/HANDOFF.md:--- ## Handoff: [TIMESTAMP] ### Current Task State [What was being worked on, current status] ### Key Decisions - [Decision 1]: [Rationale] - [Decision 2]: [Rationale] ### Modified Files - `path/to/file1.ts` - [brief description of changes] - `path/to/file2.py` - [brief description of changes] ### Blockers / Open Questions - [Any unresolved issues or questions] ### Next Steps 1. [First actionable item] 2. [Second actionable item] 3. [Third actionable item] ### Critical Context [Important gotchas, patterns, or context the next session needs] ### Model Summary - [8–12 bullets: goal, progress, key decisions, blockers, next steps] ### Handoff Context (paste into next session) [10–20 lines: actionable resume instructions, including file paths/commands] --- -
Confirm Handoff Created After writing, confirm the handoff was appended successfully and summarize what was captured.
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.
- 1mo ago First seen · 77 lines · 12 tokens per session scan A dfd0d3a60e23
create is a command published in the GitHub repository thepushkarp/handoff (12 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 688 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
lessons
View project lessons in MEMORY/LESSON.md (project root) and append a compact "never reproduce" lesson.
cleanup-context
Memory optimization - removes duplicates, consolidates knowledge, and cleans memory banks for better performance.
ctx-check
Validate claims in AI context files against the actual codebase to find stale, broken, and drifted references.
ctx-drift
Find contradictions, gaps, and inconsistencies between AI context files from different tool ecosystems.
ctx-fix
Fix staleness and drift issues found by /ctx:check and /ctx:drift with interactive proposed edits.
notes
Maintain the ROOM BRAIN — the structured state file the coach reasons from.