archive

A workflow step that implements a Beat change after its behavior description or technical proposal is complete. It can use Gherkin feature files or a proposal to drive coding and tests, including test-driven development (TDD).

In plain words
What is it for?
Use it to code a planned Beat change, implement behavior described in feature files, or continue an unfinished implementation.
Why use it?
It connects written change requirements to implementation and testing. It also gives a defined path for resuming partially completed work.

Skill for Claude CodeCodex

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 skills/kirkchen/beat/archive
Any agent
npx skills add kirkchen/beat --skill archive
Clone the repo
git clone --depth 1 https://github.com/kirkchen/beat

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,284 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.03284
Opus 5 $0.00013 $0.01642
Sonnet 5 $0.00005 $0.00657
Haiku 4.5 $0.00003 $0.00328

Measured 2d ago against content hash fb076dec41a4, 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 2d 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.

skills/archive/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Archive a completed change. Checks completion, syncs features to living documentation, then moves to archive.

<decision_boundary>

Use for:

  • Archiving a completed (or verified distilled) change
  • Syncing features into beat/features/ living documentation
  • Final living-doc sweeps (glossary terms, last-mile ADR) before archiving

NOT for:

  • Verifying implementation against spec (use /beat:verify)
  • Implementing remaining tasks (use /beat:apply)
  • Creating or modifying spec artifacts (use /beat:design)

Trigger examples:

  • "Archive the change" / "The change is done, wrap it up" / "Sync the features"
  • Should NOT trigger: "verify the implementation" / "implement the change" / "design a feature"

</decision_boundary>

Prerequisites (invoke before proceeding)

Superpower When Priority
finishing-a-development-branch After archive is complete MUST

If unavailable (skill not installed), skip and show archive summary only.

Rationalization Prevention

Thought Reality
"The change is already archived, finishing-a-development-branch is optional cleanup" Archive without branch guidance leaves orphan branches and uncommitted work. The skill ensures nothing is forgotten.
"I'll just tell the user to create a PR manually" finishing-a-development-branch offers structured options (merge, PR, cleanup) tailored to the current state. Manual advice misses context.
"Skipping sync is fine, the user can run it later" There is no separate sync skill. Archive is the only place features get synced. Skipping means features are lost from living documentation.
"The .orig backups can be cleaned up later" Orphaned .orig files hide scenarios from BDD runners permanently. Cleanup is part of archive, not a separate step.
"Glossary terms can be added later, it's just docs" Once the features sync into beat/features/, the undefined terms become user-facing living documentation. Future readers can't tell which terms are canonical vs. ad hoc. The scan-and-prompt is two minutes — do it before sync.
"We didn't write any ADRs but the design.md captures everything" design.md gets archived with the change. Cross-change decisions need to live in docs/adr/. The last-mile sweep is one prompt; if nothing qualifies, it costs nothing.
"Verify probably ran at some point, no need to check" status.yaml records it. If the verification field is absent, verify never ran — archiving unverified work silently is exactly the gap the check exists to close. One confirmation prompt, never a block.

Read the full file on GitHub · 284 lines

Files

What ships with it

4 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.

  1. 2d ago First seen · 284 lines · 26 tokens per session scan A fb076dec41a4

Subscribe to this mod's changes

archive is a skill published in the GitHub repository kirkchen/beat (7 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 3,284 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens