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 flurdy/agent-skills --skill developgit clone --depth 1 https://github.com/flurdy/agent-skillsWrote 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/flurdy/agent-skills/develop)<a href="https://agentmods.dev/skills/flurdy/agent-skills/develop"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/develop/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/flurdy/agent-skills/develop"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/develop.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 | $0.00045 | $0.00585 |
| Opus 5 | $0.00023 | $0.00293 |
| Sonnet 5 | $0.00009 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
develop 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop
A lightweight coding entry point, not another implementation workflow. Request the
runtime's configured standard/high route, then use normal repository-grounded coding
judgment. Explicit invocation is /develop <task>; in Pi use /skill:develop <task>. On Claude Code this skill carries no model: pin on purpose: it rides the session model rather than downgrading to the standard alias, while Pi routes by model-tier.
Read this skill once per new coding run, even if its text remains in context from a previous run. Use a standalone skill read before generating mutation calls. Wait for the next model response before emitting edits, writes, or shell mutations; do not bundle the read and mutations in the same response. Apply the same separation when loading a specialist below. Already-generated edits are not upgraded by a model switch.
Choose the next step
- Keep read-only requests read-only. Skill selection does not authorize edits or override plan mode, repository rules, scope, or confirmation requirements.
- If an implementation specialist already owns the work, continue it; do not restart through this entry point just to request a route.
- If a bug's cause is unknown, use diagnose-bug first.
- If consequential architecture, security, public-contract, migration, or hard-to-reverse decisions remain unresolved, use architect before coding.
- For implementation-ready work with interacting behavior, meaningful state/error paths, or local design trade-offs, load implement-solution. Reassess if an initially simple edit develops those characteristics; hand off without restarting completed work.
- Otherwise, make the smallest appropriate change using established repository patterns and proportionate tests/checks. Do not add planning, delegation, or review ceremonies merely because this skill loaded.
Routing limits
Automatic loading is best-effort, not a pre-write enforcement mechanism. Metadata requests capability; it does not prove the active model changed. Respect runtime spend and manual-selection controls; do not edit routing configuration or launch another model to force a route.
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 · 50 lines · 45 tokens per session scan A f4ffea1e9a77
develop is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 585 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 2026-09-08.
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…