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 skills/sleeyax/promptfiles/init-agentsnpx skills add sleeyax/promptfiles --skill init-agentsgit clone --depth 1 https://github.com/sleeyax/promptfilesWrote 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/skills/sleeyax/promptfiles/init-agents)<a href="https://agentmods.dev/skills/sleeyax/promptfiles/init-agents"><img src="https://agentmods.dev/badge/skills/sleeyax/promptfiles/init-agents.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 | $0.00035 | $0.00943 |
| Opus 5 | $0.00017 | $0.00472 |
| Sonnet 5 | $0.00007 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
init-agents 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Init AGENTS.md
Analyze this codebase and create an AGENTS.md file at the project root, which will be given to AI agents (Claude Code and others) operating in this repository. Also create a CLAUDE.md at the project root whose entire contents are:
@AGENTS.md
This makes Claude Code inline AGENTS.md while other tools read AGENTS.md directly, so there is a single source of truth.
Guiding principle
Agents are excellent at figuring out where code is located and how a codebase is structured — they do not need a map. AGENTS.md is a guide towards success, not a 1:1 mapping of where source code lives. Every line must pass this test: "Would removing this cause an agent to make mistakes?" If not, cut it. When in doubt, leave it out — a short file that is entirely load-bearing beats a long file that is mostly discoverable.
Workflow
1. Check for existing files
Check the project root for an existing AGENTS.md and CLAUDE.md before doing anything else.
- AGENTS.md exists: don't overwrite. Read it, explore the codebase (step 2), then propose targeted edits — additions for what's missing, removals for anything that fails the guiding principle or has gone stale. Ask before applying.
- CLAUDE.md exists with real content (anything beyond an
@AGENTS.mdimport): its content belongs in AGENTS.md. Fold the parts that survive the guiding principle into the new or existing AGENTS.md, then replace CLAUDE.md with the@AGENTS.mdstub. Ask before replacing it. - Neither exists: proceed to step 2 and write both files fresh.
2. Explore the codebase
Survey the project: manifest files (package.json, Cargo.toml, pyproject.toml, go.mod, etc.), README, Makefile/build configs, CI config, and any existing AI tool configs (.cursor/rules/, .cursorrules, .github/copilot-instructions.md, .windsurfrules, .clinerules). If the harness can spawn subagents (e.g. the Agent tool in Claude Code), delegate the survey to one to keep the file dumps out of the main context; otherwise do it inline.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 84 lines · 35 tokens per session scan A 895c9e0abbc2
init-agents is a skill published in the GitHub repository sleeyax/promptfiles (2 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 943 once invoked, 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…