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 skills/florianbruniaux/claude-code-plugins/handoff-createnpx skills add FlorianBruniaux/claude-code-plugins --skill handoff-creategit clone --depth 1 https://github.com/FlorianBruniaux/claude-code-pluginsWrote 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/florianbruniaux/claude-code-plugins/handoff-create)<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-plugins/handoff-create"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-plugins/handoff-create.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 | $0.00053 | $0.00565 |
| Opus 5 | $0.00026 | $0.00282 |
| Sonnet 5 | $0.00011 | $0.00113 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
handoff-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 today.
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
Generate a structured handoff document from our current conversation and save it to claudedocs/handoffs/handoff_YYYYMMDD_HHMMSS.md (or use the filename provided as $ARGUMENTS[0] if given).
Create the claudedocs/handoffs/ directory if it does not exist.
Document Structure
Include exactly these sections:
# Handoff: [Task Name] - [YYYY-MM-DD HH:MM]
## Task
[One sentence: what is being accomplished]
## Scope
[What needs to be done. Be specific about boundaries: what is in scope and what is explicitly out of scope]
## Files
[All relevant files touched or needed. Format: `path/to/file:line` when a specific line matters]
- `src/auth/middleware.ts:45` - token validation logic
- `tests/auth.spec.ts` - test suite for this change
- `docs/api.md` - needs update after implementation
## Discoveries
[Key findings and insights from the work so far. Things the next agent needs to know that are not obvious from the code]
- [Discovery 1]
- [Discovery 2]
## Work Done
[Completed tasks. Append-only: never remove prior entries. Include commit hashes when available]
- [x] Task A completed (commit: abc1234)
- [x] Task B completed
## Status
[Current state: what is done, what remains, test status, blockers]
## Next Steps
[Actionable checklist of remaining tasks, in order]
1. [ ] Step 1
2. [ ] Step 2
3. [ ] Step 3
## Code
[Relevant code snippets with context. Focus on the parts a resuming agent needs to understand immediately]
\`\`\`typescript
// Key implementation detail
\`\`\`
Rules
- Keep it under 600 words total. A resuming agent should be able to load this and proceed within 30 seconds of reading.
- Use
path/to/file:lineformat for all file references. Line numbers matter. - "Work Done" is append-only. Never remove previous entries.
- Do not include the full git diff or full file contents. Include only the code snippets that are non-obvious.
After saving, confirm the file path.
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.
- today First seen · 79 lines · 53 tokens per session scan A 8c9efa33e72c
handoff-create is a skill published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 565 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
vc-autopilot
Emit and validate the provisional goal block for Autopilot Mode. Owns the 9-field format and resume detection from a pasted goal block.
vc-problem-solving
Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, scale uncertainty.
thoroughness-scoring
Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.
report
Read the delivery log and say which rules actually fire, which never have, and what to prune or fix. Use when the user asks whether ballast is doing anything, wants to clean up their rule catalog, or on a periodic review.
orchestrate
Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
squid-self-improve
Analyze developer corrections from the current coding session and persist lessons learned as rules in AGENTS.md files or memory. Use at the end of a session after the developer corrected your work, when they say "squid-self-improve", ask to capture what was learned, or ask you to reflect on mistakes and extract…