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/entityprocess/allagents/agents-mdgit clone --depth 1 https://github.com/EntityProcess/allagentsWhat 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 | $0.02080 | $0.02080 |
| Opus 5 | $0.01040 | $0.01040 |
| Sonnet 5 | $0.00416 | $0.00416 |
| Haiku 4.5 | $0.00208 | $0.00208 |
Grade A, and why
allagents 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 yesterday.
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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AllAgents Repository Guidelines
This is the allagents CLI: a tool for managing AI coding assistant plugins, workspaces, and client synchronization across Claude Code, GitHub Copilot, Cursor, and related clients.
High-Level Goals
AllAgents should stay predictable, scriptable, and safe for users who manage real local workspaces:
- Keep workspace and plugin operations deterministic.
- Prefer straightforward filesystem transforms over hidden state.
- Make sync/install/update behavior easy to reason about from CLI output alone.
- Preserve user-owned config where ownership boundaries matter.
Working Style
Worktree Setup
- For any feature, bug fix, or non-trivial repo change, work from a dedicated git worktree based on the latest
origin/main. - Before starting implementation, run
git fetch originand verify your worktreeHEADis based on the currentorigin/maincommit. - Do not implement from the primary checkout, from a stale local
main, or from a branch created off an outdated base. - Default setup:
git fetch origin
git worktree add ../allagents.worktrees/<type>-<short-desc> -b <type>/<issue-or-topic>-<short-desc> origin/main
cd ../allagents.worktrees/<type>-<short-desc>
bun install
- If you discover you are not on a fresh worktree from the latest
origin/main, stop and fix that first before changing code.
Planning
- Use plan mode for any non-trivial task (5+ steps or architectural decisions).
- If something goes sideways, STOP and re-plan immediately instead of pushing through a broken approach.
- For non-trivial changes, pause and ask: "Is there a more elegant solution?" before diving in.
- Check in with the user before starting implementation on ambiguous tasks.
- Prefer automation: execute the requested work without extra confirmation unless blocked by missing information, safety concerns, or an irreversible/destructive action the user has not approved.
Bug Fixes
- Before writing code for a bug fix, confirm you understand the actual problem.
- Ask clarifying questions when the issue is vague, not reproducible from the description, could be user error, or suggests a solution that may not match the real failure.
- Do not assume the first plausible code path is the root cause. Verify the exact commands, environment, and expected versus actual behavior first.
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.
- yesterday First seen · 191 lines · 2,080 tokens per session scan A c2f1b4fbb81e
allagents AGENTS.md is an instructions file published in the GitHub repository EntityProcess/allagents (11 stars, last pushed yesterday), licensed MIT. It adds 2,080 tokens to every session, about $0.0104 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
agent-plugins codeowners.instructions.md
Instructions for awslabs/agent-plugins, covering codeowners file rules, plugins (alphabetically listed) and file must end with codeowners file.
agent-plugins copilot-instructions.md
Instructions for awslabs/agent-plugins, covering project overview, technology stack, code organization, development practices and plugin development guidelines.
EverMe AGENTS.md
Instructions for EverMind-AI/EverMe, covering agents.md, goal (pick one per pr), build & test, pre-pr checks (match ci gates) and commit & pr.
pruna-skills AGENTS.md
Instructions for PrunaAI/pruna-skills, covering pruna skills (agent notes), how it works, clarification (library-wide), install and layout.
cargo-skills AGENTS.md
Instructions for getcargohq/cargo-skills, covering cargo skills — agent guide and working in this repo.
agent-plugins-spec AGENTS.md
AGENTS.md instructions for agentplugins/agent-plugins-spec, covering agent instructions, purpose and authority, design posture, portability boundaries and editorial discipline.