A documentation tool that builds developer handoff documents from a repository and its project notes. It removes detected secrets and private information before writing the documents.

Use it to preview redactions, adjust ignored paths, and generate onboarding or handoff documentation from repository files and trove entries.

It gives a new developer or contractor the project's architecture, setup steps, conventions, decisions, and known problems without exposing personal or secret values.

ship — Skill for Claude Code by anishfyi/trove

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 anishfyi/trove --skill ship

Clone the repo

git clone --depth 1 https://github.com/anishfyi/trove

Made for: Claude Code.

Or install trove, the plugin that ships this one along with the rest of its 7 skills, 2 hooks.

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/anishfyi/trove/ship/github.svg)](https://agentmods.dev/skills/anishfyi/trove/ship)

Your own site

<a href="https://agentmods.dev/skills/anishfyi/trove/ship"><img src="https://agentmods.dev/badge/skills/anishfyi/trove/ship/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/anishfyi/trove/ship"><img src="https://agentmods.dev/badge/skills/anishfyi/trove/ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,038 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	$0.00113	$0.01038
Opus 5.5	$0.00045	$0.00415
Sonnet 5.5	$0.00023	$0.00208
Haiku 4.5	$0.00011	$0.00104

Measured 5d ago against content hash a27ce7351de0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ship 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 5d 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.

plugins/trove/skills/ship/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship (handoff docs, private info stripped)

trove ship (the trove-ship binary stays supported as an alias with the same flags) builds handoff docs from the engine index (.trove/), the project trove (./.claude/trove/entries) and well-known files (README, build manifests, agent rules, ADRs, TODO markers). A redaction pass runs on every document before anything is written. The personal user trove in ~/.claude/trove is never shipped.

Steps

Find the engine. Use the trove binary if it is on PATH. Otherwise, inside a checkout of the Trove repository, use cargo run -p trove-cli -- ship. In another repository, point cargo at a Trove checkout: cargo run --manifest-path <trove>/Cargo.toml -p trove-cli -- ship. Written SHIP below.
Preview without writing. Show the user what would be removed:
```
SHIP --repo . --dry-run
```
The report lists each removed value by placeholder ([REDACTED:email-1]), category, detector, reason, length and location. It never contains the values themselves. Summarize the counts per category for the user.
Tune .troveignore if needed. At the repo root. Bare lines are gitignore-style paths that never enter the docs. Directives, one per line:
```
secrets/
allow: [email protected]
allow-domain: example-company.dev
customer: Globex
deny: Project Nightjar
deny-regex: TICKET-\d+
internal-domain: corp-example.net
```
Ask before creating or editing this file. allow rules cannot keep a high-confidence secret.
Ship. Default output is a Markdown folder in .trove/ship/ (gitignored). Pass the user's choices through:
```
SHIP --repo . --format folder            # README.md + one file per section
SHIP --repo . --format single            # one HANDOFF.md
SHIP --repo . --format site --out docs/handoff   # static HTML site
```
Add --reindex always to refresh the engine index first. If the output directory exists and was not written by ship, it refuses unless --force is given; ask the user before forcing.

Read the full file on GitHub · 79 lines

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.

5d ago Changed · -2 lines a27ce7351de0
11d ago First seen · 81 lines · 113 tokens per session scan A 6a268050af80

Subscribe to this mod's changes

ship is a skill published in the GitHub repository anishfyi/trove (1 stars, last pushed 3d ago), licensed MIT. It adds 113 tokens to every session and 1,038 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 2026-10-16.

Claude Code Security Writing and docs claude-code-plugin context-engineering developer-tools knowledge-management markdown

reduce

Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract…

agenticnotetaking/arscontexta · 73 tokens

rethink

Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".

agenticnotetaking/arscontexta · 51 tokens

graph

Interactive knowledge graph analysis. Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions. Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis".

agenticnotetaking/arscontexta · 50 tokens

Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".

agenticnotetaking/arscontexta · 50 tokens

ralph

Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination. Supports serial, parallel, batch filter, and dry run modes. Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks".

agenticnotetaking/arscontexta · 61 tokens

remember

Capture friction as methodology notes. Three modes — explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns). Triggers on "/remember", "/remember [description]".

agenticnotetaking/arscontexta · 40 tokens