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/tzz123-hub/devwhale/agents-mdgit clone --depth 1 https://github.com/tzz123-hub/DevWhaleWrote 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/tzz123-hub/devwhale/agents-md)<a href="https://agentmods.dev/instructions/tzz123-hub/devwhale/agents-md"><img src="https://agentmods.dev/badge/instructions/tzz123-hub/devwhale/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 | $0.00048 | $0.00048 |
| Opus 5 | $0.00024 | $0.00024 |
| Sonnet 5 | $0.00010 | $0.00010 |
| Haiku 4.5 | $0.00005 | $0.00005 |
Grade A, and why
DevWhale 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 4d 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.
What it actually says
AGENTS.md
Test commands
npm test npm run lint
Loop conventions
- Report-only week one (L1) before enabling auto-fix (L2)
- See LOOP.md for cadence and human gates
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.
- 4d ago First seen · 10 lines · 48 tokens per session scan A b5ee6a6583d0
DevWhale AGENTS.md is an instructions file published in the GitHub repository tzz123-hub/DevWhale (10 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session, about $0.0002 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
ds4-control CLAUDE.md
Instructions for notatestuser/ds4-control, covering ds4 control — project guide for claude, purpose, deepseek v4 preview maintenance, stack and dev workflow.
ensemblr AGENTS.md
Instructions for ensemblr-hq/ensemblr, covering agent instructions, project naming, app scaffolding requires current official docs, package manager policy and biome policy.
threadlines AGENTS.md
Instructions for Threadlines/threadlines, covering threadlines, what threadlines cares about, a note from will, a small glossary and the three ways to hurt yourself.
clean-process-ended AGENTS.md
Instructions for MarceloCaporale/clean-process-ended, covering agents, public name vs package names, what this project is, what this project is not and working rules for agents.
hronaut AGENTS.md
AGENTS.md instructions for hronaut/hronaut, covering hronaut contributor instructions, runtime boundaries, making changes, verification and releases and adjacent repositories.
ensemblr CLAUDE.md
Instructions for ensemblr-hq/ensemblr, a project described as: macOS orchestrator for Pi and Claude Code. Every stream of work gets its own git worktree, and an agent can drive the app itself — spawn sub-agents, delegate, integrate.