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 mhylle/claude-skills-collection --skill implement-phasegit clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/mhylle/claude-skills-collection/implement-phase)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/implement-phase"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/implement-phase/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/mhylle/claude-skills-collection/implement-phase"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/implement-phase.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 | $0.00066 | $0.03866 |
| Opus 5 | $0.00033 | $0.01933 |
| Sonnet 5 | $0.00013 | $0.00773 |
| Haiku 4.5 | $0.00007 | $0.00387 |
Grade B, and why
implement-phase scanned grade B with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
# Global defaults (~/.claude/settings.json) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**You are the tester.** Not the user. API → curl/httpie/fetch subagent. Web UI → `browser-verification-agent` (one test scenario per spawn). CLI → execute and verify output. Database → query and verify. How it starts
The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Phase
Execute a single phase from an implementation plan with comprehensive quality gates. Designed to be called by implement-plan, but can also be invoked directly.
Orchestrator pattern (non-negotiable)
This session is an orchestrator. Never implement code directly.
| DO (orchestrator) | DON'T (direct implementation) |
|---|---|
| Spawn subagents to write code | Write code yourself |
| Spawn subagents to create files | Use Write/Edit tools directly |
| Spawn subagents to run tests | Run tests yourself |
| Spawn subagents to fix issues | Fix code yourself |
| Read files to understand context | Read files to copy/paste code |
| Track progress with Task tools | Implement while tracking |
| Coordinate and delegate | Do the work yourself |
Violations: using Write/Edit/NotebookEdit directly, creating files without spawning a subagent, fixing code without spawning a subagent, running implementation commands directly.
Why orchestrate?
- Context preservation — main session retains full plan context.
- Parallelization — independent tasks run concurrently.
- Clean separation — orchestration logic stays separate from implementation.
- Better error handling — subagent failures don't pollute main context.
Subagent communication protocol → references/subagent-protocol.md. Every subagent prompt must include a response-format block demanding terse STATUS/FILES/ERRORS output and disk-based logs for large output. Verbose subagent responses are the single biggest context waster this skill faces.
Execution contract (read before starting)
Steps 1–8 execute as one continuous operation. The orchestrator does not pause between them.
current_step = 1
while current_step <= 8:
result = execute_step(current_step)
if result == PASS:
current_step += 1 # AUTO-CONTINUE, no user pause
elif result == FAIL:
fix_and_retry(current_step) # Stay on step, spawn fix subagent, retry
elif result == BLOCKED:
return BLOCKED # Only valid early exit
return COMPLETE # Only stop here (after Step 8)
What ships with it
6 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 · 392 lines · 66 tokens per session scan B d3ee2b26bf0b
implement-phase is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 7d ago), licensed MIT. It adds 66 tokens to every session and 3,866 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). 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…