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 CassioRoos/godfly-skills --skill handoffgit clone --depth 1 https://github.com/CassioRoos/godfly-skillsWrote 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/cassioroos/godfly-skills/handoff)<a href="https://agentmods.dev/skills/cassioroos/godfly-skills/handoff"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/handoff/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/skills/cassioroos/godfly-skills/handoff"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/handoff.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 | $0.00057 | $0.00568 |
| Opus 5 | $0.00028 | $0.00284 |
| Sonnet 5 | $0.00011 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
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 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Write a handoff that lets a fresh agent continue without spelunking the entire conversation.
Workflow
- Identify what the next session will do. If the user gave a focus, tailor the handoff to that.
- Save the handoff outside the current repository in a durable location:
~/.codex/handoffs/(create it if missing), named<YYYY-MM-DD>-<short-slug>.md. Never use the OS temporary directory — a handoff that must survive into a future session cannot live somewhere the OS wipes. - Include only operationally useful context. Do not duplicate artifacts that already exist; reference paths, PRs, commits, docs, logs, or notebooks instead.
- Redact secrets, tokens, credentials, private personal data, and unnecessary customer data.
- Include suggested skills and why they should be used.
- Include exact commands already run only when they matter for continuation or verification.
Output Shape
# Handoff: [short title]
## Next Goal
## Current State
## Key Decisions And Evidence
## Files, Branches, PRs, Or Artifacts
## Commands Already Run
## Suggested Skills
## Risks And Open Questions
## Recommended Next Steps
Composition with toolshed
- In-repo multi-session task state lives in
docs/work/<slug>/via the toolshed skill (thin STATE + D/Q/E). Prefer updating toolshed session-end over writing a fat handoff when the next agent will open the same repo. - Handoff is for off-repo or cross-machine continuation: no clone, toolshed gitignored/local-only, or a compact note outside the tree.
- Do not re-serialize a full toolshed closeout packet into the handoff.
Point at
docs/work/<slug>/STATE.md, PR URLs, and SHAs. - Not the Workbench product/MCP (Slack/highlights app).
Rules
- Keep it compact.
- Prefer links, paths, commit SHAs, and command names over prose.
- Distinguish verified facts from assumptions.
- Say where the file was saved.
- Suggested skills should use current names (
toolshed, notworkbenchfor task state).
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.
- today Changed · +1 lines · +3 tokens per session a903003495a0
- 8d ago First seen · 66 lines · 54 tokens per session scan A a3cab623f997
handoff is a skill published in the GitHub repository CassioRoos/godfly-skills (1 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 568 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 2026-08-31.
Other skills, from other repositories
auto-test-code
A structured process for critically reviewing and testing software code. It records review findings, test plans, commands, results, and supporting files in a project workspace.
git-pr-review
A read-only reviewer for GitHub pull requests, which are proposed code changes submitted for review. It produces an evidence-based report about whether a pull request should be merged.
download-fulltext-pdf
A skill for downloading a research paper's complete PDF using an identifier such as a DOI, title, or BibTeX entry.
code-remediate
Apply selected review fixes; bare PR targets use current online items, while PR +review adds the latest matching artifact.
code-review
Close PRs at an evidence gate or review local diffs/PRs with specialists and JSON artifacts.
code-reviewer
A code-review workflow that checks completed work against its requirements or plan before merging. It groups findings by severity and gives each issue a fix and a way to verify it.