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/convocli/convosync-plugin/generate-handoffgit clone --depth 1 https://github.com/convocli/convosync-pluginWrote 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/convocli/convosync-plugin/generate-handoff)<a href="https://agentmods.dev/commands/convocli/convosync-plugin/generate-handoff"><img src="https://agentmods.dev/badge/commands/convocli/convosync-plugin/generate-handoff.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 | $0.00000 | $0.01370 |
| Opus 5 | $0.00000 | $0.00685 |
| Sonnet 5 | $0.00000 | $0.00274 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
generate-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 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.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Session Handoff
Generate a comprehensive session handoff document to sync context across devices.
What this does: Prompts Claude to generate a structured summary of the current work session, including:
- What you're working on
- Progress made
- Key decisions
- Important context (including non-code details!)
- Blockers and dependencies
- Environment setup changes
- Known issues and technical debt
- Debug/error context
- Next steps
Usage:
/convosync:generate-handoff
Execute:
cat << 'HANDOFF_INSTRUCTIONS'
╔══════════════════════════════════════════════════════════════════════╗
║ SESSION HANDOFF GENERATION ║
╚══════════════════════════════════════════════════════════════════════╝
Please generate a comprehensive session handoff document with the following
sections. This will be used to sync context when switching to another device.
────────────────────────────────────────────────────────────────────────
### Current Task
Brief description of what we're currently working on.
### Progress So Far
List of accomplishments in this session:
- ✅ Use checkmark for completed items
- ⏳ Use hourglass for in-progress items
- Be specific about what was done
### Key Decisions Made
Important technical or design decisions that were made:
- What was decided
- Why it was decided that way
- Any trade-offs considered
### Important Context
Any non-code context that's important to preserve:
- User preferences or facts mentioned in conversation
- Constraints or requirements discussed
- Assumptions made
- Background information
- Anything I said that isn't in the code but is important
### Blockers/Waiting On
What's blocking progress or what we're waiting for:
- External dependencies (API keys, permissions, etc.)
- Waiting on other teams or people
- Third-party service issues
- Missing requirements or unclear specifications
- If nothing is blocking, write "None - ready to proceed"
### Environment/Setup
Changes to development environment or setup:
- New dependencies installed (npm packages, system libraries, etc.)
- Environment variables added or changed
- Configuration file changes
- Database migrations run
- Services that need to be running (Redis, PostgreSQL, etc.)
- If no changes, write "No environment changes"
### Known Issues/Debt
Technical debt, shortcuts, or known issues:
- Shortcuts taken with file:line references (e.g., "Hardcoded timeout in auth.ts:45")
- TODOs added to code
- Known bugs or issues introduced
- Workarounds implemented
- Things that work but need improvement
- If none, write "No known issues"
### Debug/Error Context
If debugging, include error details:
- Error messages or stack traces
- Steps to reproduce the issue
- What's been tried (failed attempts)
- Current hypothesis about the cause
- If not debugging, write "No active debugging"
### Next Steps
What should be done next (numbered list):
1. Specific next action
2. Another action
3. ...
### Files Modified
List of files changed with brief description:
- filename.ts (+50, -10) - description of changes
- newfile.ts (new file) - description
### Open Questions
Any unresolved questions or pending decisions:
- Question or decision that needs to be made
- Options being considered
────────────────────────────────────────────────────────────────────────
After generating the handoff above, please save it using the Write tool to:
.convosync/session-handoff-draft.md
Then I'll run /convosync:save to commit it to the repository.
────────────────────────────────────────────────────────────────────────
HANDOFF_INSTRUCTIONS
Example handoff:
### Current Task
Implementing OAuth 2.0 authentication with Google provider and refresh token support
### Progress So Far
- ✅ Created auth.ts with login/logout/callback routes
- ✅ Implemented OAuth provider integration with Google API
- ✅ Added session management using JWT tokens
- ⏳ Currently implementing refresh token storage with Redis
### Key Decisions Made
- Using JWT tokens with 7-day expiry (balanced security vs user experience)
- Storing refresh tokens in Redis instead of PostgreSQL (faster lookup, automatic expiry)
- Google OAuth as initial provider (can add GitHub/Facebook later)
- Session cookies are httpOnly and secure (prevent XSS attacks)
### Important Context
- User mentioned their favorite pizza is Margherita (in passing conversation)
- Working in TypeScript with Express framework
- Tests will be added after core OAuth implementation is complete
- Redis must be running on localhost:6379 for development
### Blockers/Waiting On
- Waiting on production OAuth credentials from DevOps team (ETA: tomorrow)
- Need Redis Cloud account approved for staging environment
### Environment/Setup
- Installed packages: `[email protected]`, `[email protected]`, `@types/[email protected]`
- Added env vars: `REDIS_URL`, `JWT_SECRET`, `OAUTH_CLIENT_ID`, `OAUTH_CLIENT_SECRET`
- Run `npm install` and copy `.env.example` to `.env` on new device
- Redis must be running: `docker run -p 6379:6379 redis` or use local install
### Known Issues/Debt
- Session timeout hardcoded to 7 days in auth.ts:67 (TODO: move to config)
- Error handling is basic - needs proper error types and messages
- No token rotation yet (security enhancement for later)
- Refresh token endpoint returns 200 even on partial failures (needs fix)
### Debug/Error Context
No active debugging
### Next Steps
1. Finish implementing token refresh endpoint in auth.ts
2. Add comprehensive error handling for OAuth provider failures
3. Write integration tests for the complete OAuth flow
4. Update API documentation with new endpoints
### Files Modified
- src/auth.ts (+145, -10) - Added OAuth routes and token management
- src/oauth-provider.ts (+120, new file) - Google OAuth integration
- src/session-manager.ts (+85, new file) - JWT session handling
- src/types/session.ts (+45, new file) - TypeScript types for sessions
### Open Questions
- Should we implement token rotation for enhanced security? (leaning yes)
- Maximum number of concurrent sessions per user? (suggested 5)
- Should we log OAuth events for security auditing? (probably yes)
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 · 186 lines · 0 tokens per session scan A 647c3588daaa
generate-handoff is a command published in the GitHub repository convocli/convosync-plugin (4 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,370 tokens. 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
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
neo-review
Get Neo's code review with semantic matching against past findings in memory. Use on a diff or module before merge, especially where earlier mistakes in this codebase are likely to recur. Skip for formatting, lint-catchable issues, and single-line changes.