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.
npx agentmods add instructions/charlesapetersen/archive-suite/agents-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/agents-md)<a href="https://agentmods.dev/instructions/charlesapetersen/archive-suite/agents-md"><img src="https://agentmods.dev/badge/instructions/charlesapetersen/archive-suite/agents-md.svg" alt="Measured on agentmods" 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 | $0.05473 | $0.05473 |
| Opus 5 | $0.02736 | $0.02736 |
| Sonnet 5 | $0.01095 | $0.01095 |
| Haiku 4.5 | $0.00547 | $0.00547 |
Grade A, and why
Archive-Suite AGENTS.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 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.
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archive Suite — Agent / Concurrent-Development Guide
Umbrella conventions for working in this monorepo (solo or with multiple agents in parallel). Each app
also has its own AGENTS.md with app‑specific lanes — read it before working inside a subdir:
ArchiveProcessor/AGENTS.md · ArchiveReader/AGENTS.md · ArchiveNotes/AGENTS.md.
🛑 If the owner asks for the "daemon report" (or "the report", or the old name "morning review"), that is a WALKTHROUGH — one decision at a time, waiting for each answer, writing nothing. It is not a summary and not a plan entry. Read
CLAUDE.md→ "THE DAEMON REPORT IS A WALKTHROUGH, NOT A DOCUMENT" before replying. Appending to that section is the unattended daemon's job, never yours.
Ground rules
- Worktree-first — mandatory, not optional. Before any edit/build/commit, be in your own git
worktree; never work in the primary checkout, even if you think you're the only instance running. Run the
idempotent first-step check in
CLAUDE.md→ "Worktree-first" (it creates../suite-wt-<stamp>only if you're not already isolated, so it's safe to run every session). Per‑worktree DerivedData (-derivedDataPath ./build/DD, already the default in eachlaunch.sh) keeps parallel builds from colliding. Remove your worktree once your work is pushed so they don't pile up for the owner. Only ever touch worktrees you created — another agent's uncommitted WIP is not yours to clean up. Superseded 2026-07-29: the long-standing "never touch the Codex worktree~/Documents/GPT/archive-suite-processor-fixes" instruction is retired — the owner asked for it to be removed and it is gone (its work was preserved first; see §"Working the to-do list as an external agent" → Preserved work). Don't go looking for it. The standing rule is unchanged and matters more than the exception: if you find a stray worktree carrying uncommitted work, preserve it before removing anything, and never--forcepast a git refusal. - After any pull/switch,
xcodegen generate(or the app'sbootstrap.sh) — the.xcodeprojis gitignored. - Stay in your lane. A change scoped to one app touches only that subdir. Loading the other app is
almost always unnecessary (see the token‑efficiency directive in
CLAUDE.md). - Never write to a real corpus during dev/test (copy to scratchpad); never add a tag‑write call
outside Reader's audited
TagWriter, or any move/rename/delete/content‑write call anywhere. - Done = code + docs in the same commit. Ship a
SUITE_TODO.mditem → flip its checkbox (cite the commit); fix/find a bug → updateKNOWN_ISSUES.md; ship anexecution-plans/plan → delete it.SUITE_TODO.mdis the tracker of record — an unattended run reconciles it before ending, never leaning on a private plan file. The owner shouldn't have to catch a stale tracker. (Full rule:CLAUDE.md→ "Docs & backlog convention.")
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.
- 5d ago First seen · 251 lines · 5,473 tokens per session scan A 591da1e11b45
Archive-Suite AGENTS.md is an instructions file published in the GitHub repository charlesapetersen/Archive-Suite (3 stars, last pushed yesterday), licensed MIT. It adds 5,473 tokens to every session, about $0.0274 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.
Other instructions, from other repositories
Applite CLAUDE.md
Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.
Peekaboo AGENTS.md
AGENTS.md instructions for openclaw/Peekaboo, covering repository guidelines, start here, project structure & modules, build, test, and development commands and coding style & naming conventions.
scarf AGENTS.md
AGENTS.md instructions for awizemann/scarf: This repo carries its own agent memory — plain files in git, served by the in-repo memophant-mcp MCP server, managed by the Memophant macOS app. It works the same for every agent (Claude Code, Codex, Cursor, Gemini, Copilot). This block is regenerated between the memophant…
palmier-pro AGENTS.md
AGENTS.md instructions for palmier-io/palmier-pro, covering palmierpro, build, agents, engineering approach and code style.
scarf copilot-instructions.md
Copilot instructions for awizemann/scarf: File memory notes under one of six folders (architecture/conventions/decisions/operations/project/roadmap), never the root. When a note is grounded in code, pass sourcepaths (the repo files it depends on) so Memory Health can drift-check it — an unanchored code note can't be…
liney AGENTS.md
AGENTS.md instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.