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 agentmods add skills/florianbruniaux/claude-code-plugins/eval-skillsnpx skills add FlorianBruniaux/claude-code-plugins --skill eval-skillsgit clone --depth 1 https://github.com/FlorianBruniaux/claude-code-pluginsWrote 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/florianbruniaux/claude-code-plugins/eval-skills)<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-plugins/eval-skills"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-plugins/eval-skills.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 | $0.00067 | $0.02909 |
| Opus 5 | $0.00034 | $0.01455 |
| Sonnet 5 | $0.00013 | $0.00582 |
| Haiku 4.5 | $0.00007 | $0.00291 |
Grade A, and why
eval-skills scanned grade A 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.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
find .claude/skills -name "SKILL.md" 2>/dev/null Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Evaluator
Discover all skills in the project, score them across 6 criteria, and infer the appropriate effort level based on content analysis.
When to Use
- New project: run once to establish baseline quality
- Before committing a skill to a team repo
- After bulk-importing skills from another project
- When adding
effortfields for the first time - When a skill doesn't auto-trigger and you want to diagnose why
What Gets Audited
All SKILL.md files and flat .md files found in:
.claude/skills/**~/.claude/skills/**(if requested).claude/commands/**(legacy flat files, still valid)- Any path passed as argument:
/eval-skills ./my-skills-dir
Valid Frontmatter Fields
Claude Code skills follow the agentskills.io open standard, extended with Claude Code-specific fields. Flag any field not in this table as unsupported.
agentskills.io spec fields
| Field | Required | Notes |
|---|---|---|
name |
No | Display label shown in skill lists. The command name always comes from the directory name, not this field. |
description |
Recommended | Combined with when_to_use, truncated at 1,536 chars in context. First paragraph used if omitted. |
when_to_use |
No | Additional trigger phrases and example requests. Appended to description in context; counts toward the 1,536-char cap. |
allowed-tools |
No | Tools usable without per-use approval while the skill is active. Space-separated string or YAML list (both valid). |
license |
No | License identifier (agentskills.io spec) |
compatibility |
No | Compatibility constraints (agentskills.io spec) |
metadata |
No | Arbitrary metadata object (agentskills.io spec) |
Claude Code extension fields
| Field | Required | Notes |
|---|---|---|
argument-hint |
No | Hint shown during autocomplete. Example: [issue-number] or [filename] [format] |
arguments |
No | Named positional args for $name substitution. Space-separated string or YAML list. Names map to positions in order. |
disable-model-invocation |
No | true = user-only invocation. Removes skill from Claude's context and prevents preloading in subagents. |
user-invocable |
No | false = hides skill from / menu but Claude can still auto-invoke it. |
disallowed-tools |
No | Tools blocked while this skill is active. Cleared after the current message. |
model |
No | Override model for this skill's turn only. Reverts to session model on next prompt. |
effort |
No | Thinking effort: low, medium, high, xhigh, max. Overrides session effort for the turn. |
context |
No | fork = runs skill in an isolated subagent context. The skill body becomes the subagent's prompt. |
agent |
No | Which subagent type to use when context: fork is set. Options: Explore, Plan, general-purpose, or any custom agent in .claude/agents/. |
hooks |
No | Skill-scoped lifecycle hooks. Same format as session hooks. |
paths |
No | Glob patterns that limit when Claude auto-loads this skill. Same format as path-specific rules. |
shell |
No | Shell for !backtick injection: bash (default) or powershell. |
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.
- 4d ago First seen · 269 lines · 67 tokens per session scan A dbec825a7063
eval-skills is a skill published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 2,909 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
vc-autopilot
Emit and validate the provisional goal block for Autopilot Mode. Owns the 9-field format and resume detection from a pasted goal block.
vc-problem-solving
Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, scale uncertainty.
report
Read the delivery log and say which rules actually fire, which never have, and what to prune or fix. Use when the user asks whether ballast is doing anything, wants to clean up their rule catalog, or on a periodic review.
squid-self-improve
Analyze developer corrections from the current coding session and persist lessons learned as rules in AGENTS.md files or memory. Use at the end of a session after the developer corrected your work, when they say "squid-self-improve", ask to capture what was learned, or ask you to reflect on mistakes and extract…
prompt-template-guide
查看、创建、修改、删除或排查 DeterminFlow Prompt Template 与 system prompt section 时必须加载此技能；也适用于 section 顺序、workflowonly/chatonly、cache break、自定义 templatevariables、系统变量渲染以及 Agent Definition 的 prompttemplate 绑定。.
script-library-guide
创建、更新、删除、引用或排查 DeterminFlow Script Library 脚本时必须加载此技能；也适用于 Workflow Script 节点、inline 与 library 选择、SCRIPT.md、scriptargv、共享 workspace、WFVAR/scriptout 输出协议、Plugin 脚本 owner 冲突与 Task 身份冻结。.