Borrowing it
Nothing to install: this file belongs to cfpperche/picode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cfpperche/picode/main/.pi/skills/handoff-update/SKILL.mdgit clone --depth 1 https://github.com/cfpperche/picodeWrote 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/cfpperche/picode/handoff-update)<a href="https://agentmods.dev/skills/cfpperche/picode/handoff-update"><img src="https://agentmods.dev/badge/skills/cfpperche/picode/handoff-update/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/cfpperche/picode/handoff-update"><img src="https://agentmods.dev/badge/skills/cfpperche/picode/handoff-update.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 | $0.00090 | $0.01272 |
| Opus 5.5 | $0.00036 | $0.00509 |
| Sonnet 5.5 | $0.00018 | $0.00254 |
| Haiku 4.5 | $0.00009 | $0.00127 |
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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff update (ADR-0086, ADR-0123)
The handoff used to be one 485-line file that every session read, rewrote and
hand-merged (103 of 181 merges). Then it was one capped file that every session
still had to write (406 non-merge commits in ten days, 99.8% of its byte cap,
net losing text). Now: one note per session in docs/handoff/, one file
per open topic in docs/handoff/open/, and a docs/handoff.md that is
rendered, never written. If nothing changed, say so — no empty ritual.
Steps
-
Verify you are home.
git branch --show-currentandpwdmust be your branch and your worktree (the gates print the same line). Never write these files from another session's path. -
Run
make close-summary(ormake close, which ends with it). It prints the commits, the diff, the scope, the in-flight trees and the docs still owed. Write from that output, in a subagent or a fresh session — never at the peak context of the session that did the work (ADR-0105). -
Write
docs/handoff/<date>-<branch>.md, ≤ 25 lines (your note's## Next up/## Debtsbullets are the only part the board renders — the prose is for the reader):# <date> — <branch>: <one-line title> Shipped: what exists now (ADR numbers, routes, files). Verified: gates run, what was tested where (scratch instance, real tmux…), and the method's blind spot ("not run inside the Windows shell"). visual-review: PASS | FAIL | UNVERIFIED | n/a Not done / debts: what remains, honestly. Merge: fast-forward ready | merged as <sha>. ## Next up - session-local follow-up (on the board for 7 days, one bullet) ## Debts - something accepted here that outlives the branch (open until paid)Never write a line that expires. "The owner's click is the last check" is true for an hour and then rots;
not run inside the Windows shellis true forever. Record the method and its blind spot, never a pending state — nothing in the flow asks you to, and a stale pending line costs the next session real work.
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.
- 1mo ago Changed · +16 lines 5d76bab7ac5c
- 1mo ago Changed · +6 lines d8ef1004d0b1
- 1mo ago First seen · 65 lines · 90 tokens per session scan A 2c5a5952445d
handoff-update is a skill published in the GitHub repository cfpperche/picode (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,272 once invoked, about $0.0004 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 2026-09-12.
Other skills, from other repositories
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
fabric-swarm
Creates a self-organizing team of persistent Pi Fabric actors with durable topics, mailboxes, and compare-and-swap tasks. Use for messenger-like collaboration and long-lived delegated work.
board
Read and write the workspace BOARD.md (shared task board for agents + Val). Wraps bin/board, a small Python CLI that preserves the markdown schema and appends to the activity log automatically. Use this whenever an agent proposes, claims, or finishes work that should be visible to the rest of the roster.
ponytail-debt
Harvest every ponytail: comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail ledger", or…