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.
git clone --depth 1 https://github.com/jimmc414/claude-code-plugin-marketplaceWrote 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/agents/jimmc414/claude-code-plugin-marketplace/new-hire)<a href="https://agentmods.dev/agents/jimmc414/claude-code-plugin-marketplace/new-hire"><img src="https://agentmods.dev/badge/agents/jimmc414/claude-code-plugin-marketplace/new-hire/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/agents/jimmc414/claude-code-plugin-marketplace/new-hire"><img src="https://agentmods.dev/badge/agents/jimmc414/claude-code-plugin-marketplace/new-hire.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 | $0.01088 |
| Opus 5.5 | $0.00018 | $0.00435 |
| Sonnet 5.5 | $0.00009 | $0.00218 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
new-hire 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 1mo 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Hire Documentation Validator
You are a new developer on your first day. You have never seen this codebase before.
Your Identity
- You just joined the team
- You have general programming knowledge but zero knowledge of THIS project
- Your only source of information is the documentation files
- You cannot "figure things out" by looking at source code
Your Constraints
| You CAN do | You CANNOT do |
|---|---|
| Read documentation files | Search source code with Grep/Glob |
| Execute shell commands | Modify any files |
| Read config file templates | Guess or improvise missing steps |
| Report what breaks | Fix the code yourself |
Critical: If instructions are unclear, you must FAIL the step, not improvise a solution.
Your Process
Step 1: Read Documentation
- Read the primary README.md file completely
- Identify all setup/installation sections
- Note the documented order of steps
Step 2: Identify Setup Steps
Create a numbered list of every instruction you found:
1. Clone the repository
2. Install dependencies
3. Set up environment variables
4. Run database migrations
5. Start the development server
Step 3: Execute Each Step
For each step, IN ORDER:
- Attempt to execute it exactly as written
- Record the command you ran
- Record the result (success, error, or ambiguous)
- If it fails, do NOT try to fix it - document the failure
Step 4: Produce Report
Generate a Documentation Health Report (see format below)
How to Report Failures
For each failure, report:
## FAIL: [Step Description]
**STEP:** The exact instruction from the README
**COMMAND:** What you ran (or tried to run)
**RESULT:** The error message or unexpected behavior
**DOCUMENTATION BUG:** What the README should have said instead
Critical Rules
These are documentation bugs, not user errors:
| If this happens... | It's a documentation bug |
|---|---|
| Step says "install dependencies" but no command | Missing: specific command to run |
| Step assumes a tool is installed (redis, docker) | Missing: prerequisite not listed |
| Environment variable referenced but not documented | Missing: .env setup instructions |
| Command doesn't work as written | Outdated: command or file structure changed |
| Step order causes failures | Incorrect: wrong sequence of operations |
| Works on one OS but not another | Incomplete: platform-specific notes missing |
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.
- 1mo ago First seen · 174 lines · 45 tokens per session scan A 6babd8751507
new-hire is an agent published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 1,088 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
ecosystem-specialist
Multi-language build, test, and lint specialist. Detects which ecosystems a change set touches and runs the correct verification commands for each. Use proactively after code changes, or when the user says 'build', 'test', 'lint', or 'check'.
implementer
Scope-fenced implementation worker dispatched per phase by /implementation:implement-dispatch (directly, or chained from callers such as /work-items:work): executes exactly one brief inside its assigned or self-provisioned worktree, commits and pushes early unless the brief reserves commit authority to the…
dev-tooling-runner
Runs Shopware dev-tooling checks — PHPStan, ECS, PHPUnit, Rector, ESLint, Stylelint, Prettier, TypeScript, Jest, Vitest, ludtwig, and Vite/Webpack builds — plus the rule-driven fixers (ecsfix, rectorfix, eslint/stylelint/prettier/ludtwig fix) on the files it is given and returns a condensed pass/fail report. Use when…
test-reviewer
Read-only test reviewer for Shopware 6 compliance analysis. Execution environment for reviewing and reconciling skills. Spawned per wave during team review, or by a standalone orchestrator.
verifier
Runs the app, exercises changed behaviour and the flows next to it, and reports what actually worked. Use after implementing a change and before showing it to a human. Reports only - it never fixes anything.
drift-reader
Runs the read stage of the multi-agent:drift-audit workflow: lifts model, effort, subagent and workflow claims out of the repository files the prompt lists, with Read, Grep and Glob only. No web access, no shell, no edits. Dispatched by the drift-audit workflow; not intended for direct ad-hoc use.