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/hslee16/archy/claude-mdgit clone --depth 1 https://github.com/hslee16/ArchyWhat 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 | $0.01892 | $0.01892 |
| Opus 5 | $0.00946 | $0.00946 |
| Sonnet 5 | $0.00378 | $0.00378 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
Archy 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 2d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on archy
Notes for a coding agent working on this repository. For using archy as a
tool, see skills/archy/SKILL.md and the README.
Everything here was learned by getting it wrong. Each rule names the failure it came from, so you can judge whether it applies to what you are doing rather than following it blindly.
Before you push: run what CI runs
uv run ruff check # NO path argument
uv run ruff format --check
uv run ty check
uv run pytest
uv run archy check . # archy's own layer rules
uv run archy cycles . --strict
ruff check with no path. Running ruff check some/file.py is not the same
command and will pass while CI fails: a fixture directory with deliberately
unused imports broke the build twice in one session because it was only ever
linted per-file.
The last two matter as much as the first four. archy gates itself, so a new
fixture tree or bench sample can introduce a real cycle or layer violation in a
directory that is not archy's code. Add such trees to exclude: in archy.yaml
with the reason, rather than weakening a rule.
Some failures only appear in CI's environment. The bench caches under
bench/cache/ are gitignored, so a test that depends on one passes locally and
fails on the runner. Move the cache aside and re-run before pushing a test that
touches it. Assert the invariant, not the message: a test that checks which
precondition failed is asserting a fact about your laptop.
Open the failing check, never the tally. A summary line saying "1 failed"
tells you nothing; main has been broken by merging on a green-looking count.
Fetch the job's failing step, then its log.
Adding a gate or a payload field
Wire it to every surface in one change. Three at the time of writing, and
worth confirming that is still current: the CLI's text output, the CLI's
--format json, and the MCP payload. A presence check shipped to the CLI alone
left the MCP surface, the one agents actually call, reporting passed=true for
the exact case the check existed to catch. Three consecutive review rounds each
found one more surface it had been omitted from.
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.
- 2d ago First seen · 156 lines · 1,892 tokens per session scan A 0d905d30ef91
Archy CLAUDE.md is an instructions file published in the GitHub repository hslee16/Archy (7 stars, last pushed 16d ago), licensed MIT. It adds 1,892 tokens to every session, about $0.0095 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.