archiver

archiver is an agent for Claude Code from martineserios/thebrana. It costs 45 tokens per session (655 once invoked), scanned A, original, MIT.

An agent for retiring a project that reviews its accumulated knowledge and sorts findings into transferable, historical, or deletable categories. It returns the results without changing project files.

In plain words
What is it for?
Use it when closing a project to review saved knowledge, classify patterns, and decide what should be carried into future work.
Why use it?
It helps separate reusable lessons from project-specific history and information that no longer needs to be kept.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the brana plugin — 56 skills, 4 commands, 14 agents, 13 hooks shipped together

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 agents/martineserios/thebrana/archiver
Clone the repo
git clone --depth 1 https://github.com/martineserios/thebrana

Made for: Claude Code.

Or install brana, the plugin that ships this one along with the rest of its 56 skills, 4 commands, 14 agents, 13 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.

agentmods badge for archiver

README.md
[![agentmods](https://agentmods.dev/badge/agents/martineserios/thebrana/archiver.svg)](https://agentmods.dev/agents/martineserios/thebrana/archiver)
Your own site
<a href="https://agentmods.dev/agents/martineserios/thebrana/archiver"><img src="https://agentmods.dev/badge/agents/martineserios/thebrana/archiver.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 655 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 5.1 $0.00045 $0.00655
Opus 5 $0.00023 $0.00328
Sonnet 5 $0.00009 $0.00131
Haiku 4.5 $0.00005 $0.00065

Measured 5d ago against content hash 59028b7e7c70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

archiver 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.

system/agents/archiver.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Archiver

You are a project retirement agent. Your job is to scan a project's accumulated knowledge and categorize patterns for archival. You do NOT modify files — you return categorized findings to the main context.

Step 1: Gather project knowledge

Scan all knowledge sources for the project:

source "$HOME/.claude/scripts/cf-env.sh"

If found: cd $HOME && $CF memory search --query "client:{NAME}" --limit 50

Also read:

  • ~/.claude/projects/*/memory/MEMORY.md for the project
  • ~/.claude/memory/portfolio.md for the project entry
  • Project's .claude/CLAUDE.md for conventions and decisions
  • docs/decisions/ for ADRs (if they exist)

Step 2: Categorize patterns

For each pattern/learning found, classify as:

Transferable

Patterns that apply to other clients. These should be promoted:

  • Confidence >= 0.7
  • Not project-specific (general tech patterns, process patterns)
  • Worked reliably in this project

Historical

Project-specific patterns worth keeping for reference but not transferring:

  • Project-specific configurations
  • Domain-specific decisions
  • Context that explains why things were done a certain way

Deletable

Patterns that are no longer useful:

  • Low confidence patterns that were never validated
  • Temporary workarounds for bugs that were fixed
  • Stale information (outdated versions, deprecated tools)

Step 3: Portfolio impact

Check ~/.claude/memory/portfolio.md and suggest updates:

  • Mark the project as retired
  • Preserve key stats (tech stack, duration, team size)
  • Note transferable patterns that should remain accessible

Output format

## Archive Report: {Project Name}

### Transferable Patterns ({N})
{For each: key, description, confidence, suggested tags for cross-client discovery}

### Historical Patterns ({N})
{For each: key, description, why it's worth keeping}

### Deletable Patterns ({N})
{For each: key, reason for deletion}

### Portfolio Update
{Suggested changes to portfolio.md}

### Recommended Actions
1. Promote {N} patterns to transferable: true
2. Archive {N} patterns as historical
3. Delete {N} stale patterns
4. Update portfolio.md

Read the full file on GitHub · 96 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.

  1. 5d ago First seen · 96 lines · 45 tokens per session scan A 59028b7e7c70

Subscribe to this mod's changes

archiver is an agent published in the GitHub repository martineserios/thebrana (3 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 655 once invoked, about $0.0002 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 agents, from other repositories

memory-extractor

OPS specialist: Background agent that extracts user profiles, contact cards, and behavioral patterns…

Lifecycle-Innovations-Limited/claude-ops · 21 tokens

aggressive

This project keeps a local, user-owned knowledge graph of its reasoning: Decisions and their reasons, Principles, Cautions that bit us, Problems and Resolutions, Insights, open Intents, Anchors that cluster them. Not code structure — the code holds that. What good capture buys: the next session starts already knowing…

techtheist/engram · 0 tokens

archcore-auditor

Read-only documentation auditor. Use proactively for reviewing documentation health: missing relations, orphaned documents, stale statuses, coverage gaps, and consistency checks across the .archcore/ knowledge base.

archcore-ai/plugin · 43 tokens

source-ingester

Специализированный агент по ингесту внешних источников (статья, книга, видео, доклад, транскрипт, конспект лекции, экспорт цитат) в персональную базу знаний Obsidian. Делегируй сюда, когда пользователь хочет «обработать статью», «положить книгу в базу», «выжать знания из видео», «обработай конспект лекции», «разбери…

jtprogru/bear-skills · 181 tokens

brain-keeper

Maintains Agentic SEO project authorial brain pages, append-only log, source provenance, and Obsidian-compatible links.

agencia-conversion/agentic-seo-skills · 29 tokens

code-explorer

Fast, read-only code search and exploration subagent. Locates files by pattern, greps for symbols or keywords, answers "where is X defined / which files reference Y" with file:line citations and short excerpts. Spawn it to protect the orchestrator's context window from large search results — it reads excerpts, not…

ggemba/squad-mcp · 116 tokens