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 skills add odarino/haren --skill discovergit clone --depth 1 https://github.com/odarino/harenWrote 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/odarino/haren/discover)<a href="https://agentmods.dev/skills/odarino/haren/discover"><img src="https://agentmods.dev/badge/skills/odarino/haren/discover/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/odarino/haren/discover"><img src="https://agentmods.dev/badge/skills/odarino/haren/discover.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00014 | $0.00659 |
| Opus 5 | $0.00007 | $0.00329 |
| Sonnet 5 | $0.00003 | $0.00132 |
| Haiku 4.5 | $0.00001 | $0.00066 |
Grade A, and why
discover 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 9d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discover
Analyze project sources and produce a standardized context brief that feeds into the Decompose phase.
Intent Routing
Before starting discovery, determine the intent:
- User provides a raw idea (no baseline docs in
manifest.yamlsources, no repos to inherit, and input is a statement of intent) → route toideateskill. Ideate produces a concept brief, adds it tomanifest.yamlsources, and sets mode toblueprint. Discovery then proceeds in blueprint mode with the concept brief as a baseline document. - No prior context + unclear task → ask the user: "Is this research, or a new feature to design?"
- Research → route to
researchskill - New feature → route to
ideateskill (ideate now handles the research + design flow)
- Research → route to
- Module already exists + needs clarification → invoke brainstorming, output to
artifacts/04-plans/{module}/ - Module already planned → skip brainstorming, proceed to implement
Disambiguation between 0 and 1: Priority 0 triggers when the user provides an idea statement (even vague — "I want to build X"). Priority 1 triggers when there is genuinely no input and the task is unclear. The key distinction: Priority 0 has something to work with; Priority 1 has nothing.
Mode-specific behavior:
- explore mode: routes through brainstorming for collaborative design (preserved for users who explicitly set
mode: explorein manifest.yaml — the default path for new ideas is now throughideate) - blueprint mode: if baseline docs exist in
artifacts/00-baseline/, the existing blueprint strategy processes them first. Brainstorming triggers only for new features not covered by baseline docs. - inherit mode: existing codebase analysis runs first. Brainstorming triggers for new features on top of the existing code.
- undecided mode: brainstorming helps determine the mode as part of the discovery process
Process
- Read
manifest.yamlto determine mode and sources - Load the mode-specific strategy:
blueprint→ readskills/discover/blueprint.mdexplore→ readskills/discover/explore.mdinherit→ readskills/discover/inherit.md
- Follow the strategy to produce a context brief
- Write output using create-artifact skill:
artifacts/02-discovery/context-brief.md - Validate output with validate-artifact skill
- Update progress.json — project moves past discovery
What ships with it
3 files 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.
- 9d ago First seen · 55 lines · 14 tokens per session scan A 4ee859103bf1
discover is a skill published in the GitHub repository odarino/haren (11 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 659 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…