Borrowing it
Nothing to install: this file belongs to charlesapetersen/Archive-Suite. 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/charlesapetersen/Archive-Suite/main/CLAUDE.mdgit clone --depth 1 https://github.com/charlesapetersen/Archive-SuiteWrote 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/instructions/charlesapetersen/archive-suite/claude-md)<a href="https://agentmods.dev/instructions/charlesapetersen/archive-suite/claude-md"><img src="https://agentmods.dev/badge/instructions/charlesapetersen/archive-suite/claude-md/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/instructions/charlesapetersen/archive-suite/claude-md"><img src="https://agentmods.dev/badge/instructions/charlesapetersen/archive-suite/claude-md.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 | $0.09908 | $0.09908 |
| Opus 5.5 | $0.03963 | $0.03963 |
| Sonnet 5.5 | $0.01982 | $0.01982 |
| Haiku 4.5 | $0.00991 | $0.00991 |
Grade A, and why
Archive-Suite CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archive Suite — Umbrella Project Guide
Three native macOS apps in one monorepo: Archive Processor (capture · OCR · tag),
Archive Reader (find · read · triage), and Archive Notes (provenance‑first note‑taking from
archival sources). This file is the umbrella guide — repo‑wide conventions, the shared contract, and
the release process. Each app's own CLAUDE.md stays authoritative for that app; read it before
working inside a subdirectory:
ArchiveProcessor/CLAUDE.md— the Processor + its iOS/Android capture companions.ArchiveReader/CLAUDE.md— the Reader (incl. its bulletproof file‑safety Core Directive).ArchiveNotes/CLAUDE.md— Notes (provenance‑first notes + extracts from archival PDFs).
🛑 THE DAEMON REPORT IS A WALKTHROUGH, NOT A DOCUMENT — read this before answering any request for it
Trigger phrases: "daemon report", "the report", "morning review" (the old name), "anything for me?", "anything I need to decide?", "what needs my eye?", "walk me through it". Any of these means run the walkthrough below. This section exists because sessions kept getting it wrong in the same two ways, and the owner had to correct it every time.
What the owner wants, exactly: to be walked through each open decision, ONE AT A TIME, waiting for his answer before moving to the next. It is a conversation he steers. That is the whole deliverable.
❌ Do NOT do any of these — each one has actually happened and is a failure, not a variation:
- ❌ Do not write a new entry into the plan. Being asked for the report is not a cue to author one. Nothing is added to any doc during the walkthrough.
- ❌ Do not let the account of the work replace the decisions. The full account of the work comes first
(
~/Claude/CLAUDE.mdstep 3, owner 2026-10-15: detailed, read from the commit bodies), then the decisions one at a time. A recap with no decisions walked is not a report. - ❌ Do not batch the decisions into one message with a numbered list and a single "what do you think?". One decision per message. Stop. Wait.
- ❌ Do not re-raise settled items. Anything under a
### ✅ … walkthroughheading, or inSUITE_TODO.md→ "⛔ DECLINED — settled, do NOT re-raise", is closed. Reopening it wastes his time. - ❌ Do not present non-decisions as decisions. "Worth your eye, nothing blocking" is a mention, not a step. Fold those into one short block at the end, after the real decisions are done.
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 Changed · +8 tokens per session 5edec55707fe
- 5d ago Changed · +39 tokens per session 9ab7798e6ded
- 6d ago Changed · +18 lines · +512 tokens per session 8d547f4cc4aa
- 7d ago Changed · -44 lines · -833 tokens per session f08880b4bee9
- 8d ago Changed · +45 tokens per session 8a5b9530fce3
- 11d ago Changed · +18 lines · +356 tokens per session e37aafd6eda9
- 13d ago Changed · +21 lines · +626 tokens per session 94354d1fb927
- 15d ago Changed · +26 lines · +767 tokens per session b4c3396c1fc9
- 16d ago Changed · +5 lines · +110 tokens per session 709eceae4a12
- 19d ago First seen · 369 lines · 8,278 tokens per session scan A 7feb197745eb
Archive-Suite CLAUDE.md is an instructions file published in the GitHub repository charlesapetersen/Archive-Suite (4 stars, last pushed yesterday), licensed MIT. It adds 9,908 tokens to every session, about $0.0396 per session on Opus 5.5. 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.
Archive-Suite CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Archive-Suite CLAUDE.mdcharlesapetersen/Archive-Suite | Instructions file | 4 | yesterday | MIT | A | 9,908 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |