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/open-software-network/os-clovy/agents-mdgit clone --depth 1 https://github.com/open-software-network/os-clovyWhat 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 | $0.04092 | $0.04092 |
| Opus 5 | $0.02046 | $0.02046 |
| Sonnet 5 | $0.00818 | $0.00818 |
| Haiku 4.5 | $0.00409 | $0.00409 |
Grade A, and why
os-clovy 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 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
For additional context about technologies to be used, project structure,
shell commands, and other important information, read
specs/003-conversation-turns/plan.md.
Clovy — Agent Instructions
Project
Clovy is a private-by-architecture Tauri desktop app for meeting notes: it
records a meeting or dictation, transcribes the audio, turns the transcript
into a structured note, and hosts an AI agent you can chat with over your
notes. The frontend is React (src/), the native shell is Rust
(src-tauri/), and a confidential Rust backend, Clovy API (clovy-api/),
proxies all upstream AI and runs metered billing. Identity and credits come
from OS Accounts; the agent harness is a Clovy-owned TypeScript service
built on the OpenAI Agents SDK; AI models are served through Clovy's model
routing. Clovy API runs
inside a TEE (Phala) so prompt data is not readable by its own infra.
Read CONTEXT.md before naming anything, and docs/index.md to find the doc for the area you touch.
OS Platform (shared brain)
Platform-enabled repo — Product june, Team os-core, Issue prefix JUN.
The product handle and issue prefix are retained June-era technical identities;
the current product name is Clovy (see
ADR-0055).
Use the os_platform_* MCP tools (https://platform-api.opensoftware.co/mcp);
REST fallback https://app.opensoftware.co/api + Authorization: Bearer $OS_PLATFORM_API_KEY. Never print or store credentials.
Before work that will produce a branch (skip for Q&A, typos, exploration, CI):
os_platform_get_product{handle:"june"}— response embeds the Product Memory index;os_platform_get_memoryonly entries whose description touches your task.- Find-or-create the Issue:
os_platform_search_product_issuesfirst; create only if no open Issue matches the outcome. One Issue per independently reviewable outcome; reuse it across sessions. - Set the Issue
in_progress(os_platform_set_issue_statuswith the Product handle, Issue number, and status), branchJUN-<number>-<slug>, and putJUN-<number>in commit subjects and the PR title/body. PR-Links advances in_review/completed automatically where installed; if it doesn't, set them yourself. Leave unfinished work in its true status.
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 · 279 lines · 4,092 tokens per session scan A 59f69cde7024
os-clovy AGENTS.md is an instructions file published in the GitHub repository open-software-network/os-clovy (357 stars, last pushed 8d ago), licensed MIT. It adds 4,092 tokens to every session, about $0.0205 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
vzt-flow CLAUDE.md
Instructions for vonzelle-vzt/vzt-flow, covering claude.md — vzt flow, workspace layout, build / test / run, critical gotchas and verification norms.
molvi CLAUDE.md
Instructions for artanov/molvi, covering molvi — заметки для claude, работаешь на macos?, структура, команды and процессы.
humla CLAUDE.md
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
Instructions for michaelwilhelmsen/humla, covering humla — project notes, what this app is, core capabilities, architecture overview and data flow during a recording.
openquack AGENTS.md
Instructions for larryxiao/openquack, covering agents.md, posture, before you start, workflow and pr template (the required shape).
macparakeet AGENTS.md
AGENTS.md instructions for moona3k/macparakeet, covering agents.md -- macparakeet, project shape, commands, worktrees and code boundaries.