Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/archive.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote 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.
[](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/archive)<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/archive"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/archive/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.
<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/archive"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/archive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.02185 |
| Opus 5.5 | $0.00000 | $0.00874 |
| Sonnet 5.5 | $0.00000 | $0.00437 |
| Haiku 4.5 | $0.00000 | $0.00218 |
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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archive — Retire a folder/file into planning/archive/, distilling its durable residue first.
This command is brain.toml-driven and depth-agnostic. It works unchanged at a brain root, inside a
tier sub-brain (core/, portfolio/, side/, client/), or standalone outside any brain. It is the
manual archive-time gate of the D35 memory-distillation loop: nothing leaves the embedded corpus until
its durable residue has been promoted into knowledge.md / memory.md / decisions/. Archival is a
ratchet, not a drop.
The automated sweep (the
.brain-moves-pending-triggered recurring loop in D35 §4) is out of scope — a future harness. This command is the deliberate, operator-invoked version.
Variables
$ARGUMENTS — the path (relative to the cwd or absolute) of the folder or file to archive. Optionally
followed by a short reason / "what it was" note used for the archive registry row. Example:
planning/some-finished-initiative "what it was / why it's done".
Execution Model
Spawn a subagent (Agent tool) to execute all steps below; pass the resolved $ARGUMENTS and this whole
Instructions section in its prompt; return its result to the user. This command promotes durable
knowledge before deleting it from the live corpus — favour judgment over speed; use a capable model, not
the cheapest. Never move anything before Step 2's distillation is written.
Instructions
Step 0 — Resolve the manifest and the archive home
- Find the brain root. From the cwd, walk up parent by parent for a
brain.toml(its first line begins# brain.toml). Its directory isBRAIN_ROOT. If none is found, this is a standalone repo — everything below still applies locally (the file pack lives in the localplanning/); just skip any cross-repo reasoning. - Locate the owning
planning/. The archive target belongs to exactly oneplanning/— the nearestplanning/directory at or above the target. Itsplanning/archive/isARCHIVE_DIR(the warm filesplanning/knowledge.md/planning/memory.md/planning/decisions/are its siblings — the promotion destinations). IfARCHIVE_DIRdoesn't exist, create it with anindex.md(type: Index,status: archived, the "Folder · What it was · Status" table header). - Confirm the target is genuinely cold. If it looks active (recent
status: active, in-flight blocks, referenced as "now"/"next" in astatus.md), STOP and ask the operator to confirm before archiving.
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.
- 11d ago First seen · 129 lines · 0 tokens per session scan A 9b4a8642fb53
archive is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,185 tokens. 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 2026-10-26.
archive compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| archivebredmond1019/claude-sdk-rs | Command | 23 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| minutes-ideassilverstein/minutes | Command | 1.6k | yesterday | MIT | A | 48 | Claude Code, OpenCode |
| learnReflexioAI/claude-smart | Command | 791 | 3d ago | Apache-2.0 | A | 14 | Claude Code |
| memory-storeverygoodplugins/mcp-automem | Command | 66 | today | MIT | A | 10 | Claude Code |
| analyze-contextRohiRIK/OpenLtm | Command | 29 | 8d ago | MIT | A | 39 | Claude Code |
| cc-memoryTheLobbi/claude | Command | 21 | 7d ago | MIT | A | 0 | Claude Code |
| lians-recallLians-ai/Lians | Command | 17 | 4d ago | Apache-2.0 | A | 19 | Claude Code |