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 yamanidev/claude-code-configuration --skill handoffgit clone --depth 1 https://github.com/yamanidev/claude-code-configurationWrote 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/yamanidev/claude-code-configuration/handoff)<a href="https://agentmods.dev/skills/yamanidev/claude-code-configuration/handoff"><img src="https://agentmods.dev/badge/skills/yamanidev/claude-code-configuration/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/yamanidev/claude-code-configuration/handoff"><img src="https://agentmods.dev/badge/skills/yamanidev/claude-code-configuration/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 | $0.00128 | $0.01675 |
| Opus 5.5 | $0.00051 | $0.00670 |
| Sonnet 5.5 | $0.00026 | $0.00335 |
| Haiku 4.5 | $0.00013 | $0.00168 |
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 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
You are a senior engineer wrapping up a session and writing the briefing for whoever picks this work up next — possibly a fresh you, in a new conversation, with none of the context. Your job is to compact the conversation into the smallest readable handoff that lets the next agent be productive within the first minute, without re-deriving anything that's already captured elsewhere.
Operating principles
- Compact, don't transcribe. A handoff is a summary, not a log. The next agent doesn't need the full conversation — they need the state, the goal, and the next move.
- Reference, don't duplicate. Commits, PRs, diffs, ADRs, plan docs, and tickets are the authoritative sources. Link to them by path or URL. Restating their content rots the handoff the moment they change.
- Lead with the goal. The first line the next agent reads is what they're being asked to accomplish. Everything else is in service of that line.
- Name the next concrete action. After the goal, the most important line is the literal next move — what the agent should do first. If the reader gets only two lines, those are the two.
- Name the end state. Every handoff carries a single completion criterion. The next agent deduces whether it's met from the work and context, proposes resolution when confident, and deletes the file only after the user explicitly accepts. No reflexive prompting.
- Capture decisions, not deliberations. Save what was decided and the one-line reason. Don't replay the conversation that led there.
- Surface unknowns explicitly. Open questions, blocked work, assumptions made without confirmation — list them so the next agent doesn't unknowingly inherit them.
- No secrets on disk. A handoff is a file that may be read, moved, or committed. Tokens, env values, credentials, and PII never go in — reference their location instead.
- Stop after writing. The handoff is the session boundary, not a precursor to more work. Resist the urge to keep going after producing it.
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 d726c3143137
- 1mo ago First seen · 96 lines · 128 tokens per session scan A 9f2a2cc76b4e
handoff is a skill published in the GitHub repository yamanidev/claude-code-configuration (9 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 1,675 once invoked, about $0.0005 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
update
Integrate external info (research, status changes, reference material, deliverables) into the ops repo's knowledge base. Drop files in .update/ or pass content inline.
context-engine
Loads and manages company context for all C-suite advisor skills. Reads /.claude/company-context.md, detects stale context (older than 90 days), enriches context during conversations, and enforces privacy/anonymization rules before external API calls. Use when starting any C-suite advisor session, when context looks…
principle-guard-the-context-window
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
promote-memory
Review candidate learnings in Claude Code's native auto memory (/.claude/projects/ /memory/, machine-local) and run them through a five-critic council in parallel: generality, staleness, redundancy, evidence, format. Majority vote (3+ of 5) promotes the entry to MEMORY.md. Use when user says "promote memory", "review…
compress-session
Distill the current conversation into a structured note (decisions made, open questions, file pointers with line numbers, next 1–3 actions) and save to qualityreports/sessionlogs/ before auto-compression. Differs from /checkpoint (explicit stop-point snapshot) and from auto-compaction (which truncates rather than…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.