Claude-Mind: Skill for Claude Code

.claude/skills/fresh-eyes-code/SKILL.md

fresh-eyes-code is a skill for Claude Code from zkysar1/Claude-Mind. It costs 187 tokens per session (5,748 once invoked), scanned A, original, MIT.

An adversarial code review that examines selected files with the specific aim of finding bugs rather than confirming that the code is correct.

In plain words
What is it for?
Use it on chosen paths, files changed by a goal, or files changed since a given time; it produces a consistent findings report.
Why use it?
A separate review perspective can expose error paths, edge cases, platform differences, locking problems, and race conditions that the original author may miss.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is zkysar1/Claude-Mind's own configuration. It tells Claude Code how to work on Claude-Mind itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Claude-Mind configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is Bash: bash core/scripts/experience-read.sh --goal <goal-id>.

Reuse

Borrowing it

Nothing to install: this file belongs to zkysar1/Claude-Mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zkysar1/Claude-Mind/main/.claude/skills/fresh-eyes-code/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zkysar1/Claude-Mind

Made for: Claude Code.

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 fresh-eyes-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/zkysar1/claude-mind/fresh-eyes-code/github.svg)](https://agentmods.dev/skills/zkysar1/claude-mind/fresh-eyes-code)
Your own site
<a href="https://agentmods.dev/skills/zkysar1/claude-mind/fresh-eyes-code"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/fresh-eyes-code/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 fresh-eyes-code

Your own site · 80×15
<a href="https://agentmods.dev/skills/zkysar1/claude-mind/fresh-eyes-code"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/fresh-eyes-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 187 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,748 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium analysis-evasion · line 1
    Suspicious Unicode normalization or mixed-script content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
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 $0.00187 $0.05748
Opus 5 $0.00093 $0.02874
Sonnet 5 $0.00037 $0.01150
Haiku 4.5 $0.00019 $0.00575

Measured 9d ago against content hash a52040568b73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fresh-eyes-code 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 9d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Does every `subprocess.run(...)` check `returncode` or use `check=True`?
.claude/skills/fresh-eyes-code/SKILL.md · 435 lines

How it starts

The opening of the file, as written. The whole thing — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fresh-eyes-code — On-Demand Adversarial Code Review

Review a specific set of files as if seeing them for the first time, with an explicit mandate to find bugs, not confirm correctness. The author-at-write-time perspective is the worst possible one for catching structural defects — this skill schedules the mode-flip and produces a findings report regardless of outcome.

Inputs

/fresh-eyes-code <path>[ <path>...]         — Review explicit paths
/fresh-eyes-code --goal <goal-id>            — Review files touched by goal's experience trace
/fresh-eyes-code --since <timestamp>         — Review files git-changed since <timestamp>
/fresh-eyes-code --since <timestamp> --author <agent>   — Only that agent's changes (β use-case)

All sub-commands produce the same review format and findings output.

Step 0: Load Conventions

Bash: load-conventions.sh board experience journal reasoning-guardrails

Read only the paths returned. If output is empty, all conventions already loaded — proceed to next step.

Phase 1: Assemble Target Set

IF explicit paths provided:
    raw_list = list of paths (validate each exists via ls)
ELIF --goal <goal-id>:
    Bash: bash core/scripts/experience-read.sh --goal <goal-id>
    raw_list = file paths from experience.content_path + any referenced scripts/md
ELIF --since <timestamp> [--author <agent>]:
    # Canonical query — single source of truth. The script handles the
    # git-identity intersection via team-state.yaml recent_completions +
    # agents/<agent>/experience.jsonl when --author is passed. See
    # cross-agent-recent-changes.sh for semantics; do not re-describe the
    # intersection here.
    IF --author <agent>:
        Bash: bash core/scripts/cross-agent-recent-changes.sh --agent <agent> --since <timestamp>
    ELSE:
        Bash: bash core/scripts/cross-agent-recent-changes.sh --since <timestamp>
    raw_list = newline-separated stdout

# Bash-enforce the 20-file cap. Prose caps drift; a pipe does not. The cap
# preserves assembled order (recency for --since, experience order for --goal,
# argv order for explicit paths) because upstream producers already emit in
# that order — do NOT sort here.
target_files = printf '%s\n' "$raw_list" | sed '/^$/d' | head -20
skipped_count = (count of raw_list) - (count of target_files)

Read the full file on GitHub · 435 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. 9d ago First seen · 435 lines · 187 tokens per session scan A a52040568b73

Subscribe to this mod's changes

fresh-eyes-code is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed yesterday), licensed MIT. It adds 187 tokens to every session and 5,748 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.