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/kingkyylian/agentfit/agents-mdgit clone --depth 1 https://github.com/kingkyylian/agentfitWrote 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/kingkyylian/agentfit/agents-md)<a href="https://agentmods.dev/instructions/kingkyylian/agentfit/agents-md"><img src="https://agentmods.dev/badge/instructions/kingkyylian/agentfit/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 | $0.00116 | $0.00116 |
| Opus 5 | $0.00058 | $0.00058 |
| Sonnet 5 | $0.00023 | $0.00023 |
| Haiku 4.5 | $0.00012 | $0.00012 |
Grade A, and why
agentfit 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.
What it actually says
AgentFit Agent Instructions
Setup
pnpm install --frozen-lockfile
Verification
Run these before claiming completion:
pnpm typecheck
pnpm test
pnpm lint
pnpm build
pnpm smoke:package
Check the working tree with git status --short before summarizing changes.
Scope
- Keep the CLI local-first and deterministic by default.
- Do not add provider network calls to the dry-run adapter.
- Run real agent adapters only when the user explicitly selects them.
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 · 28 lines · 116 tokens per session scan A 53b110c6da3a
agentfit AGENTS.md is an instructions file published in the GitHub repository kingkyylian/agentfit (5 stars, last pushed 3mo ago), licensed MIT. It adds 116 tokens to every session, about $0.0006 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
anchor copilot-instructions.md
Instructions for peva3/anchor, covering github copilot instructions, required reading, critical rules, prohibited actions and project structure.
Harness-for-codex AGENTS.md
Instructions for ganimjeong/Harness-for-codex, covering codex harness instructions, commands, repository layout, operating principles and task loop.
anchor CLAUDE.md
Instructions for peva3/anchor: All project rules, patterns, and requirements are defined in AGENTS.md.
agents-md-doctor AGENTS.md
AGENTS.md instructions for ItsHege/agents-md-doctor, covering agents.md doctor public agent instructions, scope of this file, project goal, current baseline and working rules.
skills AGENTS.md
AGENTS.md instructions for mryll/skills, covering agents.md, skill file format and non-obvious rules.
Harness-for-codex CLAUDE.md
Instructions for ganimjeong/Harness-for-codex, a project described as: Codex harness for consistent AI-assisted development workflows, including agent instructions, standard setup/check/test/eval scripts, CI, hooks, and documentation. | AI 기반 개발 작업을 일관되게 진행하기 위한 Codex 하네스입니다. 에이전트 지침, 표준 setup/check/test/eval 스크립트…