agentmods.dev

full-eval

full-eval is a skill for Claude Code from JuanMarchetto/agent-skills. It costs 75 tokens per session (2,626 once invoked), scanned A, original, MIT.

A skill for evaluating an idea, project, or life decision from both business and personal viewpoints, then producing a PDF report.

In plain words
What is it for?
It is used to assess new projects, career moves, investments, pivots, and other decisions that affect both work and personal life.
Why use it?
It brings many kinds of assessment into one decision instead of leaving strategic and personal questions separate.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions .claude-plugin.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/user/my-saas-project.

Part of the full-eval plugin — 1 skill shipped together

not rated 5repo 7mo ago A scan 75 tokens original MIT

Good fit It is used to assess new projects, career moves, investments, pivots, and other decisions that affect both work and personal life.

Compare 6 skills from other repositories ↓
View source ↗ JuanMarchetto/agent-skills
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add JuanMarchetto/agent-skills
Claude Code
/plugin install full-eval

Made for: Claude Code.

Or install full-eval, the plugin that ships this one along with the rest of its 1 skill.

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 full-eval

README.md
[![agentmods](https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/full-eval/github.svg)](https://agentmods.dev/skills/juanmarchetto/agent-skills/full-eval)
Your own site
<a href="https://agentmods.dev/skills/juanmarchetto/agent-skills/full-eval"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/full-eval/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.

agentmods 80×15 button for full-eval

Your own site · 80×15
<a href="https://agentmods.dev/skills/juanmarchetto/agent-skills/full-eval"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/full-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,626 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00075 $0.02626
Opus 5.5 $0.00030 $0.01050
Sonnet 5.5 $0.00015 $0.00525
Haiku 4.5 $0.00007 $0.00263

Measured 2mo ago against content hash a7688d1e75e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

full-eval 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (demo/demo.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/full-eval/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Evaluation: Strategic + Personal Assessment

Evaluate any idea, project, or life decision from every angle -- 6 business evaluators and 8 life advisors running in parallel, cross-referenced into a unified verdict, delivered as a professional PDF report.

One command. Complete assessment.

When to Use This

Situation Example
Career move "Should I quit my job to build this startup?"
New project "Is this SaaS idea worth pursuing?"
Life decision "Should I relocate to another country for this opportunity?"
Investment "Should I invest 6 months into learning this technology?"
Pivot decision "My project is stalling -- should I pivot or persevere?"

Use this when the decision spans both strategic viability (will it work?) and personal fit (should I do it, now?). For purely business analysis, use architect alone. For purely personal planning, use council alone.

Dependencies

This skill composes three existing systems:

System Role Agents
Architect Strategic evaluation 6 evaluators (Risk, Technical, Market, Impact, Resources, Innovation) + synthesizer
Council Personal evaluation 8 advisors (Life Coach, Finance, Health, Career, Learning, Systems, Relationships, Creative) + synthesizer
PDF Presentation Report generation Formats the combined output as a professional PDF

The Flow

                         +-----------+
                         |   INPUT   |
                         | idea/path |
                         +-----+-----+
                               |
                    +----------+----------+
                    |                     |
              +-----v-----+        +-----v-----+
              |  ARCHITECT |        |  COUNCIL  |
              |  (parallel)|        | (parallel)|
              +-----+-----+        +-----+-----+
              |           |        |             |
        +-----+-----+    |  +-----+-----+      |
        | 6 business |    |  | 8 life    |      |
        | evaluators |    |  | advisors  |      |
        +-----+-----+    |  +-----+-----+      |
              |           |        |             |
        +-----v-----+    |  +-----v-----+      |
        | Architect  |    |  | Council   |      |
        | Synthesizer|    |  | Synthesizer|     |
        +-----+-----+    |  +-----+-----+      |
              |           |        |             |
              +-----+-----+-------+             |
                    |                            |
              +-----v-----------+               |
              | META-SYNTHESIZER |              |
              | Cross-reference  |              |
              | both outputs     |              |
              +---------+-------+              |
                        |                      |
                  +-----v-----+               |
                  |    PDF    |               |
                  |  REPORT   |               |
                  +-----------+               |

Read the full file on GitHub · 251 lines

Files

What ships with it

7 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.

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. 2mo ago First seen · 251 lines · 75 tokens per session scan A a7688d1e75e8

Subscribe to this mod's changes

full-eval is a skill published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 75 tokens to every session and 2,626 once invoked, about $0.0003 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 2026-09-03.

Claude CodeEvaluationPlanningai-agentsai-toolsautomationbrowser-automation
Related

full-eval compared with skills from other repositories

full-eval next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
full-evalJuanMarchetto/agent-skillsSkill57mo agoMITA75Claude Code
x402browser-use/browser-useSkill121kyesterdayMITA166Claude Code
browser-usebrowser-use/browser-useSkill121kyesterdayMITA54Claude Code, Codex
open-sourcebrowser-use/browser-useSkill121kyesterdayMITA101Claude Code
remote-browserbrowser-use/browser-useSkill121kyesterdayMITA22Claude Code
cloudbrowser-use/browser-useSkill121kyesterdayMITA177Claude Code
opencli-autofixjackwener/OpenCLISkill31k4d agoApache-2.0A61Claude Code