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 revenantworks/claude-skills --skill revenantworks-foundation-handoffwrightgit clone --depth 1 https://github.com/revenantworks/claude-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/revenantworks/claude-skills/revenantworks-foundation-handoffwright)<a href="https://agentmods.dev/skills/revenantworks/claude-skills/revenantworks-foundation-handoffwright"><img src="https://agentmods.dev/badge/skills/revenantworks/claude-skills/revenantworks-foundation-handoffwright/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/revenantworks/claude-skills/revenantworks-foundation-handoffwright"><img src="https://agentmods.dev/badge/skills/revenantworks/claude-skills/revenantworks-foundation-handoffwright.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 | $0.00157 | $0.03355 |
| Opus 5.5 | $0.00063 | $0.01342 |
| Sonnet 5.5 | $0.00031 | $0.00671 |
| Haiku 4.5 | $0.00016 | $0.00335 |
Grade A, and why
revenantworks-foundation-handoffwright 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
revenantworks-foundation-handoffwright
history in CHANGELOG.md · sources in SOURCES.md · Apache-2.0 (LICENSE)
A session that pauses without a written handoff loses its own state the moment anything touches
the working tree — a git stash, a reset, a worktree switch, a teleport to a new session.
handoffwright exists for one reason: write the handoff and commit it in the same call, so the
record survives whatever happens to the tree next. It is not a summarizer and not a diary — every
line it writes is checked against git, never taken on a session's own word.
Workflow: Gather (git, the ledger if one exists, this session's own record) → Write (the template shape) → Commit (same call, same repo) → Report the sha and emit the paste-ready starter prompt for the next chat
Load budget
Every write reads references/handoff-template.md for the section shape. Nothing else — no
second reference file to open, no doctrine file, no lookup. A resume reads the committed file
back directly; it does not re-open the template. now adds references/now.md.
Dependencies (standalone profile): as the compatibility field states — git for verify, stash
check and commit (absent: claims marked unverified, commit reported skipped); native file tools
(absent: in-chat content the user saves, said so); promptwright and dispatchwright optional.
Optional mods: references/mods.md, only when their data is present.
Entry points
Bare invocation ("handoffwright", no task): reply exactly — "handoffwright here. I write every
kind of handoff — this session's own state verified against origin, with its decisions and the
ordered remainder, or a forward task brief for a future session to execute (handoffwright resume reads one back, checking git stash list and
git reflog first; now hands it to a fresh agent). Inside an active dispatchwright fan-out its own ledger already covers this;
I'm for everything else. Write the handoff now?" — and stop.
Write (default entry — "handoffwright", "write the handoff", "hand off"/"handoff", "give me a
prompt to hand off", "pause here", "holding position", a usage-limit or compaction warning, or any
request to leave a record before a session ends or hand work to a later reader): the entry above
covers bare invocation only; any of these phrases carrying a reason to write now skips the
question and runs Write directly. An auto-compaction is enough only when this same session
carries on the work; when another session, agent or person will pick it up, a committed handoff
is still owed (observation #0210). A context line alone is not a reason for a new session:
compact at a quiet point instead (pacewright references/modes.md); a new session with a
handoff is for the end of a work block or a switch of repo or project.
What ships with it
21 files 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.
- CHANGELOG.md 2.7 KB
- evals/behaviour-starter-prompt/graders/fenced.md 101 B
- evals/behaviour-starter-prompt/graders/fires.md 175 B
- evals/behaviour-starter-prompt/graders/honest-commit.md 346 B
- evals/behaviour-starter-prompt/prompt.md 221 B
- evals/nearmiss-resume-fanout/graders/stays-quiet.md 249 B
- evals/nearmiss-resume-fanout/prompt.md 127 B
- evals/RESULTS.md 8.8 KB
- evals/test-cases.md 12 KB
- evals/trigger-evals.md 10 KB
- evals/trigger-pause/graders/fires.md 199 B
- evals/trigger-pause/prompt.md 124 B
- LICENSE 11 KB
- NOTICE 593 B
- README.md 5.3 KB
- references/handoff-template.md 13 KB
- references/mods.md 1.2 KB
- references/now.md 3.0 KB
- references/pack.md 41 KB
- SOURCES.md 5.2 KB
- volatile.json 86 B
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 · +1 tokens per session 99820a6af493
- 15d ago Changed · -68 tokens per session 92691bb94b3b
- 19d ago First seen · 179 lines · 224 tokens per session scan A daca01bbe829
revenantworks-foundation-handoffwright is a skill published in the GitHub repository revenantworks/claude-skills (2 stars, last pushed today), licensed Apache-2.0. It adds 157 tokens to every session and 3,355 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-07.
Other skills, from other repositories
claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.
setup-pre-commit
A setup for Husky pre-commit checks in a JavaScript or TypeScript repository. A pre-commit hook runs automatically before a Git commit and can format staged files, check types, and run tests.
ratchet-files
Ratchet source file size so every file stays small enough for an agent to read whole: find every file over a token budget, split oversized files by concept, and set up the pre-commit ratchet that stops them from growing. Use when a commit is blocked because a file is over the size budget, when asked to find or split…
releasing-godot-prompter
Use when cutting a GodotPrompter release or bumping its version — the version-bump sequence, tag-triggered workflow, and the marketplace manifests that must follow.
push-all
Use when the user explicitly asks to stage all current changes, create a commit, and push to the remote after safety checks.
review-gate
Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when explicit implementation approval is missing. Trigger for review gate, review pack, approve before landing, diff first then land, human approval, merge gate, commit gate, push gate, or PR readiness.…