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/iamv4g/dnd_kit/agents-mdgit clone --depth 1 https://github.com/iamv4g/dnd_kitWhat 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 | $0.00405 | $0.00405 |
| Opus 5 | $0.00202 | $0.00202 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
dnd_kit 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.
What it actually says
Agent Instructions
Project-specific authority:
README.mdanddocs/product/define current product behavior.docs/ARCHITECTURE.mdanddocs/decisions/define package boundaries and lasting technical choices.- Use the focused package tests during development and the Melos validation
lanes documented in
README.mdbefore claiming repository-wide proof.
Harness
Start with the requested outcome, then use the repository as the system of
record. Read docs/WORKFLOW.md and only the product, design, plan,
code, and validation material relevant to the task.
- Answers, explanations, reviews, diagnoses, plans, and status reports are read-only. Inspect only what is needed and do not mutate repository or Harness state.
- For a bounded change, use an ephemeral plan: inspect the affected behavior and existing proof, implement the change, and run behavior-appropriate validation. No control-plane operation is required.
- Create or update one file under
docs/plans/active/when work spans sessions, needs coordination or an ordered sequence, has meaningful dependencies, or requires explicit recovery steps. Move it todocs/plans/completed/only after validation. - Before editing, identify repository authority for each new externally observable policy. If materially different choices remain open, stop before edits; configurable defaults are not authority.
- Also pause when product intent remains ambiguous, an action is difficult to recover, validation would be weakened, or the request does not authorize the needed action.
- Claim completion only with relevant executable or observable evidence. Report the outcome, important changed surfaces, validation, and unresolved risks.
SQLite intake, story, trace, scoring, audit, and proposal commands are optional compatibility features. Use them only when explicitly requested or required by an external orchestrator.
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 · 41 lines · 405 tokens per session scan A 4310803320dd
dnd_kit AGENTS.md is an instructions file published in the GitHub repository iamv4g/dnd_kit (2 stars, last pushed 16d ago), licensed MIT. It adds 405 tokens to every session, about $0.0020 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
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
wind dynamic.instructions.md
Instructions for fluttersdk/wind, covering dynamic json renderer (lib/src/dynamic/), json schema, security model (whitelist first), state binding (id-keyed widgets) and action dispatch.
wind tests.instructions.md
Instructions for fluttersdk/wind, covering test conventions (test/), layout mirror, required setup, no mockito and lifecycle discipline.
wind docs.instructions.md
Instructions for fluttersdk/wind, covering documentation conventions (doc/), file shape (every doc file), wfoo, basic usage and props.
leopardo-hr AGENTS.md
Instructions for kitokoh/leopardo-hr, covering agents.md - guide de travail leopardo rh, ⚡ spec-driven development — spec kit (nouveau 2026-08-14), commandes disponibles (github copilot skills), presets actifs (injectes automatiquement dans toute spec) and workflow standard (remplace la creation manuelle d'issues).
dart-sdk-skills AGENTS.md
Instructions for RandalSchwartz/dart-sdk-skills, covering ai agent developer handbook (agents.md), 🎯 repository purpose, 🔄 runbook 1: updating for new dart sdk releases, 🔄 runbook 2: updating for new flutter framework releases and 📏 quality & style guidelines.