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/slowdini/slow-powers/agents-mdgit clone --depth 1 https://github.com/slowdini/slow-powersWhat 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 | $0.00881 | $0.00881 |
| Opus 5 | $0.00441 | $0.00441 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
slow-powers 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slow-powers
Slow-powers is a set of software development methodology skills and meta skill-writing guidance.
What lives here
This repo ships Slow-powers across four harnesses:
skills/— Skills, assets, and cross-cutting tests.claude-plugin/— Claude Code plugin.codex-plugin/— OpenAI Codex pluginopencode/— OpenCode plugin (@slowdini/slow-powers-opencode)cline/— Cline plugin (CLI/SDK/Kanban only; declared via theclinefield inpackage.json, withskills/auto-discovered from the package root)
Cline-specific setup for working on this repo also lives at root:
.clinerules/— Cline rules (the Memory Bank custom instructions), trackedmemory-bank/— Cline Memory Bank contents. Gitignored: each developer keeps their own local bank; only the rule in.clinerules/is shared
Editing the right files
Two file-confusion traps are common in this repo. Avoid both:
- Write memory-file changes to
AGENTS.md, the only real file.CLAUDE.md(and any future harness-specific memory files) are symlinks toAGENTS.md. EditAGENTS.mddirectly; the symlinks reflect it automatically. Never try to "fix up" the other names — there's nothing to fix. - Read and edit only files inside this repository, never the installed
slow-powers plugin. Your environment almost always has the slow-powers
plugin installed while this repo is the bleeding-edge
devsource. The two trees diverge, so an installed skill file is not the file you want. Every read and edit belongs to a path under this project directory.
Cross-Harness Compatibility
All skills MUST use cross-harness vocabulary, as described in slow-powers/writing-skills.
Pull Request Requirements
- Read existing skills before proposing changes to skill content. Skill prose has been tuned over many iterations upstream and downstream; changes to behavior-shaping content (Red Flags tables, rationalization lists, "human partner" language) need evidence the change is an improvement.
- Test your change on at least one harness and note which one in the PR description. If your change touches harness-specific infrastructure, test that harness.
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 · 85 lines · 881 tokens per session scan A 9bd921f0987a
slow-powers AGENTS.md is an instructions file published in the GitHub repository slowdini/slow-powers (2 stars, last pushed 19d ago), licensed MIT. It adds 881 tokens to every session, about $0.0044 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
Trellis CLAUDE.md
Claude Code instructions for mindfold-ai/Trellis, covering claude.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
Trellis AGENTS.md
AGENTS.md instructions for mindfold-ai/Trellis, covering trellis instructions, gitnexus — code intelligence, always do, never do and resources.
truthmark AGENTS.md
Instructions for merlinhu1/truthmark, covering authority, documentation scope, product boundary, rules and instruction surface boundary.
claude-dev-workflow CLAUDE.md
Instructions for TouheedCode/claude-dev-workflow, covering claude-dev-workflow, what this is, getting started, project structure and commands.
ai-auto-work CLAUDE.md
Claude Code instructions for chaohong-ai/ai-auto-work, covering gamemaker - ai native 游戏创作平台, 项目简介, ai 工作目录约定 and 按需加载（不默认装载）.
ai-auto-work AGENTS.md
AGENTS.md instructions for chaohong-ai/ai-auto-work, covering gamemaker agent context, agent 专用上下文, 双模型协作架构 and 补充约定.