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-updatenpx skills add FlorianBruniaux/claude-code-plugins --skill handoff-updategit 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-update)<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-plugins/handoff-update"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-plugins/handoff-update.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 | $0.00060 | $0.00582 |
| Opus 5 | $0.00030 | $0.00291 |
| Sonnet 5 | $0.00012 | $0.00116 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
handoff-update 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update an existing handoff document with this session's progress.
Step 1: Resolve the Handoff File
Determine which file to update, in this priority order:
- If
$ARGUMENTS[0]was provided, use it as the file path. - If this session was started via
/handoff:resume, look in conversation history for the argument that was passed to it. - If neither is found, fall back to creating a new file:
claudedocs/handoffs/handoff_YYYYMMDD_HHMMSS.md. Inform the user that no existing handoff was found.
Step 2: Read the Existing File
Read the resolved file completely. Parse all sections as the baseline for the merge.
Step 3: Apply Section Merge Rules
Rewrite the file with updated content using these merge rules:
| Section | Rule | Notes |
|---|---|---|
| Task | Keep original | Update only if scope fundamentally changed |
| Scope | Keep or refine | Narrow it if new understanding emerged |
| Files | Merge | Add new files touched in this session. Keep originals. Use path:line format |
| Discoveries | Append | Add new findings below existing list. Never remove prior discoveries |
| Work Done | Append only | Add new completed items below existing list. Never remove entries. Include commit hashes |
| Status | Replace | Write the current state: what is done now, what remains, test status |
| Next Steps | Replace | Write the updated actionable checklist |
| Code | Update | Replace with the most relevant snippets from the current state |
The append-only rule for Work Done is strict. Even if a previous entry describes work that was later revised, keep it. The history is the record. Add a new entry describing the revision instead of removing the old one.
Step 4: Confirm
After saving, confirm:
- File path updated
- How many new Work Done items were added
- The updated Status (one line)
- How many Next Steps remain
This command implements the Handoff Triad pattern documented in this guide's Session Handoff Pattern section. Template inspired by Packmind's handoff commands (Apache 2.0).
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 · 52 lines · 60 tokens per session scan A 6bd4d8c71e18
handoff-update is a skill published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 582 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…