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/yi427/cloister/agents-mdgit clone --depth 1 https://github.com/yi427/CloisterWrote 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/yi427/cloister/agents-md)<a href="https://agentmods.dev/instructions/yi427/cloister/agents-md"><img src="https://agentmods.dev/badge/instructions/yi427/cloister/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 | $0.00268 | $0.00268 |
| Opus 5 | $0.00134 | $0.00134 |
| Sonnet 5 | $0.00054 | $0.00054 |
| Haiku 4.5 | $0.00027 | $0.00027 |
Grade A, and why
Cloister 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 3d 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.
What it actually says
Repository guidance
Cloister is a security-boundary product. Prefer explicit, inspectable behavior over hidden defaults.
Scope
- Keep the first product terminal-first and macOS/Apple-container focused.
- Treat the profile schema as a public contract and version it.
- Keep Apple
containercommand construction separate from CLI presentation. - Never silently mount host credential directories or privileged sockets.
- Never claim that a bind-mounted workspace is protected from writes made by the guest.
- Never equate a named container network with blocked internet access.
Workflow
- Keep changes small and reviewable in Git.
- Do not commit local profiles, credentials, runtime state, or agent transcripts.
- Keep focused module tests beside their Rust modules and put public-behavior,
cross-module, and CLI tests under
tests/. - Store deterministic test data under
tests/fixtures/; never use real credentials, home-directory state, or machine-specific absolute paths there. - Run
make formatafter editing Rust code andmake verifybefore considering a change complete. - Keep
.githooks/pre-commitaligned withmake verify; the hook must validate the staged snapshot without modifying or staging the working tree. - Add focused tests when profile parsing or command construction is introduced.
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.
- 3d ago First seen · 29 lines · 268 tokens per session scan A eae13dacdf25
Cloister AGENTS.md is an instructions file published in the GitHub repository yi427/Cloister (2 stars, last pushed 22d ago), licensed Apache-2.0. It adds 268 tokens to every session, about $0.0013 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
apfel CLAUDE.md
Instructions for Arthur-Ficial/apfel, covering apfel - project instructions, the golden goal, core product (this is what apfel is), byproducts (useful, but not the pitch) and readme.md structure rule.
stenoai CLAUDE.md
Claude Code instructions for stenolabs/stenoai, covering claude.md, architecture, development commands, backend (python) and desktop app (electron).
speech-swift AGENTS.md
AGENTS.md instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
stenoai AGENTS.md
AGENTS.md instructions for stenolabs/stenoai, covering agents.md, code review rules, bundled binaries with an api, bare exit() in python and platform parity.
humla CLAUDE.md
Claude Code instructions for michaelwilhelmsen/humla, covering humla — project notes, what this app is, core capabilities, architecture overview and data flow during a recording.
humla AGENTS.md
AGENTS.md instructions for michaelwilhelmsen/humla, covering humla — project notes, what this app is, core capabilities, architecture overview and data flow during a recording.