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 skills add Ozzeron/prompt-pack --skill handoffgit clone --depth 1 https://github.com/Ozzeron/prompt-packWrote 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/ozzeron/prompt-pack/handoff)<a href="https://agentmods.dev/skills/ozzeron/prompt-pack/handoff"><img src="https://agentmods.dev/badge/skills/ozzeron/prompt-pack/handoff.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.00977 |
| Opus 5 | $0.00046 | $0.00489 |
| Sonnet 5 | $0.00018 | $0.00195 |
| Haiku 4.5 | $0.00009 | $0.00098 |
Grade A, and why
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 2d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Handoff
You just finished (or are about to finish) a coding task. This skill produces a structured handoff so the human reviewer or the next agent can verify the work without re-reading every file. It also surfaces risks, follow-ups, and proactive suggestions — without expanding scope unilaterally.
When to use
- After completing any non-trivial code change
- Before opening a PR (this output adapts to a PR description)
- When passing work to another agent or person
Skip for one-line edits or quick answers — overhead exceeds value.
Scope
In scope:
- What changed and why
- How to verify (commands, URLs, manual checks)
- Risks and edge cases the author considered
- What was left out and why
- Suggestions the author noticed but didn't act on (with priority)
Out of scope:
- Marketing the work — be neutral, no "successfully implemented"
- Restating the entire diff line by line
- Scope expansion: suggestions stay in the suggestions section, not as silent changes
Inherits
meta/engineering-principles— used implicitly: if the work violates these, the handoff must call it out under Risks or Suggestions.meta/token-discipline— build the handoff from working memory, not by re-reading files.
Token discipline (specific)
Inherit meta/token-discipline. Additionally:
- Build the handoff from your own working memory of the task. Do not re-read every changed file.
- Quote file paths and line ranges, not file contents.
- If you can't remember a detail without re-reading — say "verify this" rather than fabricate.
Output format
## Summary
<2-4 sentences: what was done and why it matters>
## Changes
- `<file>` — <one-line description>
- `<file>` — <one-line description>
## How to verify
1. <Concrete step: run X, open Y, check Z>
2. ...
## Tested
- ✅ <what was actually tested, automated or manual>
- ⚠️ <what was assumed, not verified>
## Risks / edge cases
- <Edge case considered and how it's handled, or why it's acceptable>
## Out of scope (not done)
- <Thing the user might expect but wasn't included, with reason>
## Suggestions
> Surface only. Not applied. User decides.
- **Must:** <something that should be done soon, e.g. a follow-up bug exposed by this work>
- **Nice-to-have:** <improvement worth doing if time allows>
- **Out-of-scope idea:** <larger thing for a separate task>
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +4 lines · +62 tokens per session e6ab84235b7d
- 8d ago First seen · 103 lines · 29 tokens per session scan A b56888fc1f44
handoff is a skill published in the GitHub repository Ozzeron/prompt-pack (8 stars, last pushed 2d ago), licensed MIT. It adds 91 tokens to every session and 977 once invoked, about $0.0005 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 skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
sdd-research
Trigger: SDD research, external evidence, source-backed research. Produce auditable evidence for a selected research lane.