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/letya999/whipnext/agents-mdgit clone --depth 1 https://github.com/letya999/whipnextWrote 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/letya999/whipnext/agents-md)<a href="https://agentmods.dev/instructions/letya999/whipnext/agents-md"><img src="https://agentmods.dev/badge/instructions/letya999/whipnext/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 | $0.01165 | $0.01165 |
| Opus 5 | $0.00583 | $0.00583 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
whipnext 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 5d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
whipnext
Click a pack character overlay; it plays an animation/sound and injects a phrase into the focused coding-agent session. Default phrase is next. It is not a slash-command launcher. Stack: Rust 2021, wry/tao settings UI, layered overlay. License: MIT.
Read first
| Document | When to open |
|---|---|
| docs/product.md | Before adding a user-facing flow or arguing priority. |
| docs/architecture.md | The change crosses pack, overlay, settings, or inject. |
| docs/engineering.md | Stack, layout, where to put a file, git flow. |
| docs/quality.md | Adding or renaming a check. |
| docs/branching.md | Branch or merge rules. |
Commands
Only through just. Flags and tool paths live in justfile.
| Command | What it does |
|---|---|
just |
list recipes |
just setup |
rustfmt, clippy, ESLint install |
just fmt-check |
rustfmt check |
just clippy |
clippy -D warnings |
just lint-js |
ESLint on assets/ui |
just test |
cargo test |
just detect |
release --detect JSON |
just dev |
settings + overlay, inject traces in ~/.whipnext/dev.log |
just check |
fmt-check + clippy + lint-js + test |
A change is not done until just check passes.
How to work
Think before code. If the request is ambiguous, ask; do not guess. Simple. Minimum that solves the task. Nothing for later. Local. Touch only what the task needs. Do not rewrite working overlay/UI paths to clean them up. From the goal. State the check first. Every step has a verification. Fail closed. If a check fails or context is missing, stop and say so.
Source of truth
User task -> docs/ (this file included) -> code, tests, and git history as evidence.
Old chat, closed tasks, and commit messages are not requirements unless restated.
Agent authority
Inside the task, do reversible local work through a verified result without asking again at each step.
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.
- 5d ago First seen · 93 lines · 1,165 tokens per session scan A a901834c2496
whipnext AGENTS.md is an instructions file published in the GitHub repository letya999/whipnext (1 stars, last pushed 12d ago), licensed MIT. It adds 1,165 tokens to every session, about $0.0058 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
openscreen AGENTS.md
AGENTS.md instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
cezar AGENTS.md
AGENTS.md instructions for open-mercato/cezar, covering agents.md — working in this repository, zero config, changing a mechanism that already works, the http api and repository layout.
hardproof AGENTS.md
AGENTS.md instructions for asimons81/hardproof, covering hardproof agent instructions, project identity, read order, architecture map and release infrastructure.
ai-usage-widget AGENTS.md
Instructions for odrasile/ai-usage-widget, covering agents.md, goal, working principles, workflow and technical constraints.
codex-pets AGENTS.md
Instructions for astandrik/codex-pets, covering agents.md, commands (verified), workflow, file map and golden samples (follow these patterns).
telltale CLAUDE.md
Claude Code instructions for sanlee-ys/telltale, covering telltale — contributor contract, build and test, golden tests: the actual workflow and its traps, a council test never spawns a vendor and a council test never writes the operator's own state.