What is handoff-trace?

A requirements-traceability skill for linking requirements, specifications, and tests through layers of project documents. Traceability means being able to follow each requirement through its implementation and verification.

Use it to define document layers, connect acceptance criteria to verification results, check coverage, and update trace links.

It helps reveal missing links, uncovered requirements, and changes that need to be checked again.

handoff-trace — Skill for Claude Code and Codex by alphaelements

Install

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.

Any agent

npx skills add alphaelements/handoff-mcp --skill handoff-trace

Clone the repo

git clone --depth 1 https://github.com/alphaelements/handoff-mcp

Made for: Claude Code, Codex.

Or install handoff-mcp, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alphaelements/handoff-mcp/handoff-trace/github.svg)](https://agentmods.dev/skills/alphaelements/handoff-mcp/handoff-trace)

Your own site

<a href="https://agentmods.dev/skills/alphaelements/handoff-mcp/handoff-trace"><img src="https://agentmods.dev/badge/skills/alphaelements/handoff-mcp/handoff-trace/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/alphaelements/handoff-mcp/handoff-trace"><img src="https://agentmods.dev/badge/skills/alphaelements/handoff-mcp/handoff-trace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,565 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00138	$0.03565
Opus 5.5	$0.00055	$0.01426
Sonnet 5.5	$0.00028	$0.00713
Haiku 4.5	$0.00014	$0.00357

Measured yesterday against content hash 1258c7881c79, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

handoff-trace 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 yesterday.

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.

plugin/skills/handoff-trace/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff Trace Skill (V-model traceability)

The entry point for the V-model system built on top of handoff_doc_*: what it is, how to switch it on, how a project moves through it, and which tool to call. Details live in reference files — read the one you need:

need	read
Writing requirements / specs / test items, IDs, attributes, requirement trees	the `handoff-requirements` skill
Every trace tool's parameters and outputs, CLI equivalents	references/tools.md
Every `[trace]` config key, layers, profiles, `auto_layer`	references/config.md
Every lint rule and how to fix it, policy rules, `quality_prompt`	references/lint-rules.md
Recording results, test ingestion, campaigns, approval, layer status, done guard, bug flow, reports	references/verification.md
Hashes, baselines, suspects, impact analysis, change proposals, sync rules, data locations	references/change-management.md
Moving `doc_req_import` requirements into a layer document; upgrading older projects	references/migration.md
One requirement carried end to end, with every call	references/walkthrough.md

1. Mental model

 definition (left)                              verification (right)
 requirement   REQ/FR/NFR  ── verified by ──▶  acceptance   AT/AC
   │ refined by                                    ▲
 basic_spec    SPEC/BS     ── verified by ──▶  system_test  ST
   │ refined by                                    ▲
 detailed_spec DS          ── verified by ──▶  unit_test    UT
        ▲ implements                                ▲ executes
      tasks ────────────────────────────────────── tasks

Layer document — a document saved with doc_save(layer=...). Its Markdown body is the source of truth; each ### <ID> title heading is one item, and the bullet list right under it holds the item's attributes.
Links — refines (detail an upper left item), verifies (a right item checks a left item, optionally one acceptance criterion REQ-003#AC2), and parent (decompose within one layer: the requirement tree).
Acceptance criteria — a 受入基準: / Acceptance criteria: block under an item; under the minimal/bugfix profiles each criterion becomes its own verification item automatically.
Tasks — handoff_update_task(requirement_ids=[...]) links a task to items with role implements (left side) or executes (right side).
Three independent axes per item: dev_stage (implementation, driven by implementing tasks), state (verification, from recorded results: passing / failing / blocked / not_run / uncovered), approval (draft → review → approved; editing the definition resets it to draft).
Coverage — horizontal (does it have a verifier?) and vertical (is it refined downward?), each covered / partial / waived / uncovered / na. Under implicit-acceptance profiles "covered" is not "verified" — read state for that.
Suspects — every link remembers the hash of what it pointed at. When the upstream definition changes, the link (and linked tasks, and passing results) become suspect until someone reviews and clears them. Spread is one hop.
Project-level — layer statuses (per-layer approval lifecycle), project baselines (coverage snapshots), verification campaigns (manual checklists with evidence), change proposals (deltas), and generated reports.

Read the full file on GitHub · 230 lines

Files

What ships with it

8 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.

Changes

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.

yesterday Changed · +2 lines 1258c7881c79
3d ago Changed · -721 lines · +49 tokens per session 4c013a053277
4d ago Changed · +99 lines 7df7eec54d0b
7d ago Changed · +8 lines 6331d5aab5ce
10d ago Changed b298247cf922
14d ago Changed · +45 lines 1d45b9a976ae
18d ago First seen · 797 lines · 89 tokens per session scan A 87c4758fa551

Subscribe to this mod's changes

handoff-trace is a skill published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 138 tokens to every session and 3,565 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 2026-10-03.

Planning Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

handoff-trace