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 AbdurRafay2004/handoff --skill setupgit clone --depth 1 https://github.com/AbdurRafay2004/handoffWrote 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/abdurrafay2004/handoff/setup)<a href="https://agentmods.dev/skills/abdurrafay2004/handoff/setup"><img src="https://agentmods.dev/badge/skills/abdurrafay2004/handoff/setup/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/abdurrafay2004/handoff/setup"><img src="https://agentmods.dev/badge/skills/abdurrafay2004/handoff/setup.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 | $0.00102 | $0.01396 |
| Opus 5.5 | $0.00041 | $0.00558 |
| Sonnet 5.5 | $0.00020 | $0.00279 |
| Haiku 4.5 | $0.00010 | $0.00140 |
Grade A, and why
setup 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 15d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up handoff in this repo
Scaffold the durable project-memory system, then populate it from the real codebase so it ships useful — not blank. Discovery drafts; the user confirms before anything is saved. Never invent project facts (RULES rule 5).
0. Locate templates & detect existing install
- The template tree is bundled with this plugin at
../../templates/relative to this skill file (i.e.<plugin-root>/templates/). Resolve that absolute path. - Check whether
.handoff/already exists in the project root:- Exists → do NOT overwrite. Tell the user it's already set up; offer to refresh specific files (e.g. re-run discovery for STATUS/MAP/TECH_STACK) or seed a CONTEXT.md. Stop here unless they choose a refresh.
- Absent → continue.
1. Copy the template tree
Copy the bundled templates/ into the project as .handoff/, preserving
structure (BOOT, RULES, STATUS, MAP, CHANGELOG, context/, docs/ with
SKILL-WORKFLOW.md, tasks/ with inbox/now/done). Keep the .gitkeep files.
Do not edit RULES' universal section.
Write the current plugin version into .handoff/VERSION (single line) — the
SessionStart hook uses it for template-drift detection.
Read the version from .codex-plugin/plugin.json in Codex or
.claude-plugin/plugin.json in Claude Code; use the available manifest if only
one is packaged.
2. Guided discovery (read the repo — do not guess)
Read what actually exists, quietly:
- Build/manifest files:
package.json,pyproject.toml,go.mod,Cargo.toml,composer.json,Gemfile, Makefile, CI config, framework config files. - Top-level directory layout and the largest/most-central source folders.
git log --oneline -20and current branch for recent direction.- Any existing README for product intent. Derive: project name, type, primary stack, common commands (build/dev/test/lint), deploy target, and the verify commands for RULES rule 10.
3. Draft, then CONFIRM before saving
Present concise drafts for the user to correct:
- STATUS.md — Current State (where the repo stands now), Active Work (none unless evident), Blockers (none unless evident). Keep ≤ 25 lines.
- context/TECH_STACK.md — stack, commands, env vars, deploy, verify commands.
- MAP.md — entry points, key directories, where to make common changes.
- context/PRODUCT.md — only if a README/product intent is discoverable; otherwise leave the template prompts and say so.
- Replace the
<PROJECT_NAME>/<PROJECT_TYPE>/<PRIMARY_STACK>placeholders in BOOT.md. Wait for the user's confirmation/edits. Only then write the files. For anything you cannot determine from the repo, leave the template prompt in place rather than inventing — and tell the user what you left blank.
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.
- 15d ago Changed · +13 lines fc5d2d261f5f
- 1mo ago First seen · 88 lines · 102 tokens per session scan A 8ecb2858999e
setup is a skill published in the GitHub repository AbdurRafay2004/handoff (4 stars, last pushed 10d ago), licensed MIT. It adds 102 tokens to every session and 1,396 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 2026-08-31.
Other skills, from other repositories
checkpoint
Write the current working state (task, decisions, files touched, open problems, next steps) to .amber/STATE.md so it survives compaction and session restarts. Use when the user asks to checkpoint/save state, before risky long operations, when context feels heavy, or before ending a work session.
resume
Reload saved working state from .amber/ (STATE.md, FOCUS.md, checkpoint.md) and continue the previous task. Use when the user says resume/continue where we left off, or at the start of a session in a project that has an .amber directory.
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.
agent-common
Use when a cc10x agent starts a task: the shared preamble for the memory protocol, the contract format, and the output rules.
decision-ledger
Maintain an append-only decision ledger (DECISIONS.md). Use when the user confirms a decision, reverses or changes a past decision, asks what was decided and why, or at session start to load standing decisions.
pin
Turn a correction or working preference the user just expressed into a permanent ballast rule. Use when the user corrects your behavior, says "don't do X" / "always do Y" / "I told you before", or asks you to remember how they want things done.