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/kenn-io/agentsview/agents-mdgit clone --depth 1 https://github.com/kenn-io/agentsviewWhat 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 | $0.01307 | $0.01307 |
| Opus 5 | $0.00654 | $0.00654 |
| Sonnet 5 | $0.00261 | $0.00261 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
agentsview 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 today.
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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Scope
- These rules apply to all agent work in this repository.
- Requests to review, analyze, or explain are read-only unless the user also asks for changes.
- Read every focused guide whose route matches the task before editing files.
- More specific instructions override broader ones.
- Keep
CLAUDE.mdas a symlink to this file. Record new durable rules here or in the matching focused guide.
Task Routes
| Task or path | Read before editing |
|---|---|
| Features, bug fixes, tests, or test helpers | docs/agents/testing.md |
| SQLite, PostgreSQL, CockroachDB, DuckDB, archive resync, or storage queries | docs/agents/storage.md |
| Watchers, polling, sync scheduling, background work, or memory investigations | docs/agents/background-work.md |
| Build commands, toolchains, CI build tags, or dependencies | docs/agents/build.md |
S3 ingest, S3Provider, or Source.S3Discovery |
docs/agents/s3-providers.md |
| Any frontend file | frontend/AGENTS.md |
| Frontend controls, styling, or reusable components | frontend/AGENTS.md and DESIGN.md |
The README.md and Makefile are the sources for project facts, setup, and
commands. Do not copy their catalogues into this file.
Roborev
- Never run
roborev reviewunless the user asks for it. - Never invoke a roborev skill, including
roborev-fixorroborev-design-review-branch, unless the user asks for that skill. - Other roborev commands may be used when they fit the task.
Git and Delivery
- Check the branch state before editing. Do not create or switch branches without the user's permission. A Codex-managed detached worktree may receive commits; leave branch creation to the user or app.
- Commit every turn that changes tracked files. Do not make empty commits. If a turn is read-only or changes only ignored files, say that no commit was made.
- Keep commits focused and use clear conventional commit messages.
- Do not amend, squash, rebase, push, or pull unless the user asks.
- Do not add generated-with lines, attribution blocks, validation footers, or command transcripts to commit messages.
- Deliver changes through pull requests from feature branches. Never merge a pull request; merging is the user's decision.
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.
- today Changed · +4 lines · +59 tokens per session 0c3ef295f035
- 2d ago First seen · 121 lines · 1,248 tokens per session scan A bb9ce485de97
agentsview AGENTS.md is an instructions file published in the GitHub repository kenn-io/agentsview (5,707 stars, last pushed today), licensed MIT. It adds 1,307 tokens to every session, about $0.0065 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
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.
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).
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.