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/steinsfu/my-adhd-caveman/agents-mdgit clone --depth 1 https://github.com/SteinsFu/my-adhd-cavemanWhat 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 | $0.00578 | $0.00578 |
| Opus 5 | $0.00289 | $0.00289 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
my-adhd-caveman 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide
Map for agents installing or changing my-adhd-caveman. Canonical behavior lives in skills/my-adhd-caveman/SKILL.md. This file does not replace it.
Start here
README.md— purpose, skill install vs always-on.INSTALL.md— per-client install and always-on paths.skills/my-adhd-caveman/SKILL.md— the skill.rules/README.md— whyrules/is not auto-loaded.
Do not read secrets, home-directory config, or unrelated caches. Run only commands the user asked for.
Repository map
| Area | Location | Purpose |
|---|---|---|
| Canonical skill | skills/my-adhd-caveman/SKILL.md |
Source of truth |
| Gemini opt-in command | skills/my-adhd-caveman/agents/gemini.toml |
Copy to ~/.gemini/commands/ |
| Skill mirrors | .cursor/skills/, .agents/skills/ |
Symlinks to the canonical skill |
| Claude / Codex | .claude-plugin/, .codex-plugin/, .agents/plugins/ |
Plugin + marketplace manifests |
| Other runtimes | plugin.json, gemini-extension.json, kimi.plugin.json, qwen-extension.json, GEMINI.md, package.json |
Antigravity, Gemini extension, Kimi, Qwen, Pi |
| Always-on templates | rules/ |
Opt-in copy-paste. Not auto-loaded. |
Source-of-truth rules
- Change
skills/my-adhd-caveman/SKILL.mdfirst. Mirrors are symlinks; do not duplicate the body. - Keep versions aligned across
.claude-plugin/plugin.json,.codex-plugin/plugin.json,package.json, and the other manifests. disable-model-invocation: trueis intentional: install ≠ always-on.- Do not add
alwaysApplyunder.cursor/rules/in this repo. Always-on is a user copy fromrules/.
Install for the user
Follow INSTALL.md for the client they named. Default if they did not name one:
npx skills add SteinsFu/my-adhd-caveman -g
Do not copy rules/ unless they asked for always-on.
Credits (do not load at runtime)
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 · 46 lines · 578 tokens per session scan A 908fb66d62ae
my-adhd-caveman AGENTS.md is an instructions file published in the GitHub repository SteinsFu/my-adhd-caveman (2 stars, last pushed 13d ago), licensed MIT. It adds 578 tokens to every session, about $0.0029 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
claude-adhd-skills CLAUDE.md
Instructions for ravila4/claude-adhd-skills, covering about me, development environment, about you, technical knowledge and foundational rules.
ai-toolkit AGENTS.md
Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
superpowers-reasonix AGENTS.md
Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.
ai-mind AGENTS.md
Instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
vvvv-skills CLAUDE.md
Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.