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.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 5.1 | $0.00045 | $0.01088 |
| Opus 5 | $0.00023 | $0.00544 |
| Sonnet 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 8d 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.
- 8d 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 yesterday), licensed MIT. It adds 45 tokens to every session and 1,088 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 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'.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
test-generator
Test generator for Shopware 6 tests. Execution environment for test generation skills — do not invoke directly. Skills fork into this agent via context: fork. Does not review tests — use the appropriate reviewer agent for that.
test-expert-csk
Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".
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, and returns a verdict plus identifiers. Not intended for…
test-engineer
Writes and runs unit tests verifying the change and preventing regressions. Follows project test framework conventions.