A command that archives merged feature specifications in project memory, keeps information about their source, and can scan for older merged specifications. It supports selecting which archive records to update.

Use it to archive a completed feature or sweep the project for older features that should be moved into durable records.

It preserves important feature decisions and history after merging while helping identify specifications that have not yet been archived.

archive — Command for coding agents by racecraft-lab: A command that archives merged feature specifications in project…

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.

agentmods

npx agentmods add commands/racecraft-lab/paddock/archive

Clone the repo

git clone --depth 1 https://github.com/racecraft-lab/Paddock

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/commands/racecraft-lab/paddock/archive.svg)](https://agentmods.dev/commands/racecraft-lab/paddock/archive)

Your own site

<a href="https://agentmods.dev/commands/racecraft-lab/paddock/archive"><img src="https://agentmods.dev/badge/commands/racecraft-lab/paddock/archive.svg" alt="Measured on agentmods" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,101 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod 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	$0.00016	$0.03101
Opus 5	$0.00008	$0.01550
Sonnet 5	$0.00003	$0.00620
Haiku 4.5	$0.00002	$0.00310

Measured yesterday against content hash b3d7af22baad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

archive 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.

Origin

This is a copy

100% identical to speckit.archive.run — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.specify/extensions/archive/commands/archive.md · 428 lines

How it starts

The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Act as the Chief Software Architect, Documentation Maintainer, and release provenance auditor.

Your goal is to archive merged feature specifications into durable project memory while preserving enough provenance to recover raw spec artifacts from git later. This command also supports Archive Sweep mode, which identifies previously merged feature specs before a new SpecKit run starts.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding.

Input Parsing

Parse $ARGUMENTS as shell-like tokens. Supported forms:

speckit.archive.run specs/###-feature-name [scope] [provenance] [mode]
speckit.archive.run --sweep --current-target specs/###-current-feature [provenance] [mode]

Positional Input

First non-option token: feature spec directory path, for example specs/007-invoice-settings.
In --sweep mode, no positional feature directory is required.

Scope Modifiers

If none are provided, update all archival artifacts.

--spec-only: update only .specify/memory/spec.md
--plan-only: update only .specify/memory/plan.md
--changelog-only: update only .specify/memory/changelog.md
--agent-only: update only the agent knowledge file (GEMINI.md, AGENTS.md, or CLAUDE.md)

Mode And Safety Options

--dry-run: do not modify files; produce the same eligibility, provenance, and cleanup report that an apply run would use.
--apply: apply memory archival edits. This is the default for a single feature archive unless --dry-run is present.
--sweep: discover previously merged feature specs and report archive and cleanup eligibility before any new spec work begins.
--apply-cleanup: after successful archival, remove or move completed spec folders out of active specs/** only if every cleanup gate passes.
--current-target <path>: active feature spec for the current run. Archive Sweep MUST exclude this path from archival and cleanup.

Provenance Options

Read the full file on GitHub · 428 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.

yesterday First seen · 428 lines · 16 tokens per session scan A b3d7af22baad

Subscribe to this mod's changes

archive is a command published in the GitHub repository racecraft-lab/Paddock (11 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 3,101 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to speckit.archive.run, differing in 0 lines, and is treated as a copy.

Memory and context agent-orchestration ai-agents github-issues nextjs software-factory sqlite

remember

Stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Supports recording architectural decisions, anti-patterns, tool preferences, workflow outcomes, and project conventions that persist across sessions. Use when saving patterns, remembering…

yonatangross/orchestkit · 62 tokens

memory

Unified read-side memory operations including knowledge graph search, session context loading, decision timeline viewing, and Mermaid graph visualization. Subcommands: search, load, history, viz, status. Complements /ork:remember (write-side). Use when searching past decisions, loading context, or visualizing the…

yonatangross/orchestkit · 64 tokens

dream

Nightly memory consolidation — prunes stale entries, merges duplicates, resolves contradictions, rebuilds MEMORY.md index. Use when memory files have accumulated over many sessions and need cleanup. Do NOT use for storing new decisions (use remember) or searching memory (use memory).

yonatangross/orchestkit · 55 tokens

archive