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/shadowru/perimeter/claude-mdgit clone --depth 1 https://github.com/Shadowru/perimeterWhat 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 | $0.01386 | $0.01386 |
| Opus 5 | $0.00693 | $0.00693 |
| Sonnet 5 | $0.00277 | $0.00277 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
perimeter 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 72 lines · 1,386 tokens per session scan A 5aef107cec38
perimeter CLAUDE.md is an instructions file published in the GitHub repository Shadowru/perimeter (11 stars, last pushed 18d ago), with no licence file. It adds 1,386 tokens to every session, about $0.0069 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 2026-08-30.
Other instructions, from other repositories
OpenIntegrations AGENTS.md
Instructions for Bayselonarrend/OpenIntegrations, covering руководство для agents, каноничный исходный код, каноничные тесты, описание релизов and зеркало onescript.
1c-ssl-skills CLAUDE.md
Instructions for brake71/1c-ssl-skills, covering инструкции для ai-агентов, назначение репозитория, структура, локальные источники бсп and работа со скилом.
bsl-ai-toolkit AGENTS.md
Instructions for vgtitov/bsl-ai-toolkit, covering правило №0: перед работой — синхронизация, версионный стек — настрой под свой проект, главное правило: спроси инструмент, не угадывай, слои контура — настрой and гейт структурных правок (человек / ai).
bsl-ai-toolkit CLAUDE.md
Instructions for vgtitov/bsl-ai-toolkit, covering claude code — специфика (поверх общих правил agents.md), скиллы (авто-подхват по описанию задачи), хуки (детерминированные проверки), mcp and поиск по коду.
1c_hbk_bsl AGENTS.md
Instructions for mussolene/1c_hbk_bsl, covering oacs / acs repository workflow and repository python runtime.
1c_hbk_bsl CLAUDE.md
Instructions for mussolene/1c_hbk_bsl: Use OACS/ACS for substantial repository work as the governed local context, evidence, and checkpoint layer. OACS records facts and proof; it does not choose or run tools for the assistant.