analyze-jd

analyze-jd is a command for coding agents from fourleafai/clover-public. It costs 0 tokens per session (950 once invoked), scanned B, original, MIT.

A command that compares a resume with a job description and gives a fit score with missing areas.

In plain words
What is it for?
Assessing whether to apply, finding gaps in experience or skills, and reviewing a pasted job description against the user's Four-Leaf resume.
Why use it?
It helps identify how well an application matches a role without asking you to provide the stored resume again.

Command

Part of the four-leaf plugin — 1 skill, 7 commands, 2 MCP servers shipped together

Install

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.

agentmods
npx agentmods add commands/fourleafai/clover-public/analyze-jd
Clone the repo
git clone --depth 1 https://github.com/fourleafai/clover-public

Or install four-leaf, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 2 MCP servers.

Wrote 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.

agentmods badge for analyze-jd

README.md
[![agentmods](https://agentmods.dev/badge/commands/fourleafai/clover-public/analyze-jd.svg)](https://agentmods.dev/commands/fourleafai/clover-public/analyze-jd)
Your own site
<a href="https://agentmods.dev/commands/fourleafai/clover-public/analyze-jd"><img src="https://agentmods.dev/badge/commands/fourleafai/clover-public/analyze-jd.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 950 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00950
Opus 5 $0.00000 $0.00475
Sonnet 5 $0.00000 $0.00190
Haiku 4.5 $0.00000 $0.00095

Measured 4d ago against content hash e5f22a6c7ddf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

analyze-jd scanned grade B with 1 finding 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 4d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- Don't lecture about resume best practices in general. Focus on this resume vs. this JD.
skills/four-leaf-coach/references/commands/analyze-jd.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

analyze-jd

Score a resume against a job description and point out the gaps.

When to run

  • User says "should I apply for this?" or "how does my resume look against this JD?".
  • User pastes a job description and asks for a fit assessment.

Flow

  1. Ask for the JD only. The user's resume already lives on their Four-Leaf account; match_score pulls it automatically. Don't ask them to paste it. Short prompt:

    Paste the job description and I'll score the fit against your Four-Leaf resume.

    If the user sends a job-posting URL instead of pasted text, fetch the page with your own WebFetch tool and use the result as the JD. match_score does not fetch URLs server-side; it expects plain text. If WebFetch isn't available or the page won't render, fall back to asking the user to paste the JD body.

  2. Wait for the JD. If it's a short fragment, ask for the full posting before scoring; a stub gives an unreliable score.

  3. Call match_score with only the jobDescription argument. Omit resume; the tool pulls the master resume from the user's account and scores against that. The output carries resumeSource so you know what was evaluated. If the tool returns error: "no_master_resume", tell the user briefly that there's no resume on their account yet and direct them to uploadResumeUrl to upload one, then call the tool again once they confirm. If the user explicitly wants to score a different version of their resume (e.g. one they're drafting right now), pass it via the resume argument as an override.

  4. Present the score clearly. Lead with the headline:

    Match score: 72 out of 100. Solid fit with real gaps.

    Then break it down:

    • What matched well. Pull the strongest 3-5 from the matched skills.
    • What's missing. Pull required skills the resume doesn't mention. Be specific.
    • Calibration. Score 80+ = apply with current resume. 60-79 = apply, but tailor first. Below 60 = either the role isn't a fit or the resume buries relevant work.

Read the full file on GitHub · 49 lines

Changes

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.

  1. 4d ago First seen · 49 lines · 0 tokens per session scan B e5f22a6c7ddf

Subscribe to this mod's changes

analyze-jd is a command published in the GitHub repository fourleafai/clover-public (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 950 tokens. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.