A command that searches the Claude Archive, a collection of previously solved coding-agent tasks, before solving a new problem.

Use it to search archived solutions, inspect high-scoring matches, take a matching solution, verify it, adapt it, and test the result.

It can reveal an earlier solution or useful lead, while requiring the result to be checked against the current project before use.

CAA-search — Command for Claude Code by ofirbuchshtav-lgtm

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.

Clone the repo

git clone --depth 1 https://github.com/ofirbuchshtav-lgtm/claude-archive

Made for: Claude Code.

Or install claude-archive, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 MCP server.

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/ofirbuchshtav-lgtm/claude-archive/caa-search/github.svg)](https://agentmods.dev/commands/ofirbuchshtav-lgtm/claude-archive/caa-search)

Your own site

<a href="https://agentmods.dev/commands/ofirbuchshtav-lgtm/claude-archive/caa-search"><img src="https://agentmods.dev/badge/commands/ofirbuchshtav-lgtm/claude-archive/caa-search/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/commands/ofirbuchshtav-lgtm/claude-archive/caa-search"><img src="https://agentmods.dev/badge/commands/ofirbuchshtav-lgtm/claude-archive/caa-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 421 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	$0.00021	$0.00421
Opus 5	$0.00010	$0.00211
Sonnet 5	$0.00004	$0.00084
Haiku 4.5	$0.00002	$0.00042

Measured 12d ago against content hash 53b5f1f1557a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

CAA-search 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 12d 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.

commands/CAA-search.md · 24 lines

What it actually says

Search the Claude Archive for: $ARGUMENTS

Locate the Archive (first that exists wins)

$ARCHIVE_HOME env var
~/.claude-archive.json → {"home": "<path>"}
bin/archive.mjs in the current project or a sibling claude-archive/ folder
None → offer to clone: git clone https://github.com/ofirbuchshtav-lgtm/claude-archive ~/claude-archive (then it becomes home). If cloning is declined, search the live site instead: fetch https://ofirbuchshtav-lgtm.github.io/claude-archive/index/index.json and match titles/tags against the query.

Procedure

If the Archive folder has a git remote, git pull --ff-only quietly first (fresh knowledge).
Run: node bin/archive.mjs search "$ARGUMENTS" from the Archive home (or MCP tool archive_search if connected).
Present the top hits with their scores and status to the human in one compact list.
Best hit scored ≥ 70 → node bin/archive.mjs take <id> and read it fully. Verify against the current project before applying — a 79 means "good with almost no changes", never blind trust. Adapt, test, then act.
Best hit < 70 → treat as a lead only; verify everything.
No hit → say so, solve the problem normally, and remind the human that /CAA-add afterward turns the solution into the next Claude's search hit.
If you took: you owe a give-back this session (give / score / log organize). Check with node bin/archive.mjs stats. Small and fair is enough.

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.

12d ago First seen · 24 lines · 21 tokens per session scan A 53b5f1f1557a

Subscribe to this mod's changes

CAA-search is a command published in the GitHub repository ofirbuchshtav-lgtm/claude-archive (0 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 421 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.

Claude Code Research agents ai claude knowledge-base llms-txt

CAA-search

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Locate the Archive (first that exists wins)

Procedure

What this file has done since we first saw it

Other commands, from other repositories

review

cli-test

dev-setup

blz

deps-audit

auto-browse