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 agentmods add skills/luisfelipemoro/harness-devkit/handoffnpx skills add LuisFelipeMoro/Harness-devkit --skill handoffgit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWrote 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/luisfelipemoro/harness-devkit/handoff)<a href="https://agentmods.dev/skills/luisfelipemoro/harness-devkit/handoff"><img src="https://agentmods.dev/badge/skills/luisfelipemoro/harness-devkit/handoff.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.00472 |
| Opus 5 | $0.00032 | $0.00236 |
| Sonnet 5 | $0.00013 | $0.00094 |
| Haiku 4.5 | $0.00006 | $0.00047 |
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.
What it actually says
Compact the conversation into a single, standalone handoff document. Save to /tmp/handoff-<YYYY-MM-DD-HHMMSS>.md. Print the path and a 3-line summary.
Also update the Harness memory file: write/refresh PROGRESS.md at the repo root (Done / Failed / Current State / Next / Lessons — schema in references/progress-file.md). The /tmp handoff is the rich narrative; PROGRESS.md is the durable, committed state the SessionStart bootstrap hook reads next session. The two must agree.
Rules
- Point to existing artifacts (PRD, delivery file, ADR) rather than recreating them
- If a delivery is in flight, record its identity first: the
Delivery-Key, the delivery file path, the release branch, the worktree path, and which story is next. Without the key the next session cannot resume the delivery — it will derive a fresh one and fork the work. Same for a bug fix: record thehotfix/{slug}branch. - Redact API keys, passwords, and PII
- Record the session's
Lessons— every rule the session learned the hard way, each with the failure or gate output that taught it./handoffis the only writer of that section, and it is the one part ofPROGRESS.mdmeant to outlive the delivery; a handoff that skips it discards the session's most durable output. Nothing learned this session is the only valid reason to omit it. - The Suggested skills section is mandatory — it helps the next session start with the right tool
- If arguments provided, tailor the document toward that next-session objective
Document format
Follow the structure in references/handoff-template.md (Task, Status, Key decisions, Files changed, Next steps, Suggested skills).
What ships with it
2 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.
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 · +4 lines d37f386232e9
- 4d ago First seen · 21 lines · 65 tokens per session scan A b8399b111fbf
handoff is a skill published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 472 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.