Claude-Mind: Skill for Claude Code

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

fresh-eyes-program is a skill for Claude Code from zkysar1/Claude-Mind. It costs 152 tokens per session (9,693 once invoked), scanned A, original, MIT.

A scheduled review of the project’s shared purpose and whether the participating agents still support it, run after every 100 completed goals.

In plain words
What is it for?
Use it to review the program’s direction, both agents’ summaries, the shared portfolio, recent completions, and warning signs of drift.
Why use it?
It provides a regular check for drift in the overall program or between the agents’ work and that program.

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/fresh-eyes-record-tick.sh last_fresh_eyes_program_review --claim.

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-program/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-program

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/zkysar1/claude-mind/fresh-eyes-program"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/fresh-eyes-program.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,693 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

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 →

  • high Rogue Agent · line 238
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • high Rogue Agent · line 246
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 $0.00152 $0.09693
Opus 5 $0.00076 $0.04847
Sonnet 5 $0.00030 $0.01939
Haiku 4.5 $0.00015 $0.00969

Measured 9d ago against content hash 6f0ffd0042ab, 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-program 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 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.

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.

.claude/skills/fresh-eyes-program/SKILL.md · 637 lines

How it starts

The opening of the file, as written. The whole thing — 637 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fresh-eyes-program — Periodic Shared-Purpose Self-Audit

Every 100 completed goals (or on user demand), step back and produce a shared-purpose briefing examining two questions:

  1. Is The Program still the right shared purpose for this world?
  2. Do both agents' Selfs still serve The Program, or are they drifting?

The ritual runs autonomously, writes the briefing to agents/<agent>/temp/, and posts a one-line summary to the coordination board. No email push, no user-approval gate. The user reviews changes via git log and tracked signals at their own pace.

Sibling Relationship

Sibling to /fresh-eyes-review. Both rituals share infrastructure (fresh-eyes-cadence-check.sh, fresh-eyes-record-tick.sh) but target different scopes:

Ritual Scope Cadence WM slot
/fresh-eyes-review Per-agent Self + portfolio 25 goals last_fresh_eyes_review
/fresh-eyes-program World shared purpose + team alignment 100 goals last_fresh_eyes_program_review

Sub-commands

/fresh-eyes-program                 — User-forced review, bypasses cadence gate
/fresh-eyes-program --cadence       — Check cadence; run only if gate passes
                                      (agent-invoked path from precheck)

Step 0: Load Conventions

Bash: load-conventions.sh with each name from the conventions: front matter. Read only the paths returned. If output is empty, all conventions already loaded — proceed.

Phase 1: Cadence Gate

IF invoked with --cadence:
    # Run this ALONE, in its own Bash call. Do NOT batch it with the 1.1 claim
    # below (see "Never batch the gate with the claim").
    Bash: core/scripts/fresh-eyes-cadence-check.sh --config-block fresh_eyes_program
    # Read the OUTPUT TEXT, not just the exit code: the gate prints its verdict
    # ("noop (…)" vs a fire line) on stdout, and a trailing pipe (| tail, | head)
    # replaces the gate's rc with the pipe's (guard-1150). A "noop" line means
    # DONE regardless of what rc you observed.
    IF noop / exit 1: Output "Fresh-eyes-program: cadence not crossed — noop." → DONE (return)
                      Do NOT run 1.1. A non-running agent must never hold the claim.
    IF exit 0: proceed
ELSE (user-invoked, no --cadence flag):
    Proceed directly — user override.

# 1.1 CLAIM the shared ritual (g-115-3218, 2026-07-28) — the FIRST action once
# committed to running, on BOTH paths above (a user-invoked pass is just as
# much a duplicate risk to a sibling as a cadence-invoked one).
# PRECONDITION: the gate above did NOT noop. This line is conditional, not
# unconditional — reaching it means this agent is about to run the ritual.
Bash: bash core/scripts/fresh-eyes-record-tick.sh last_fresh_eyes_program_review --claim

Read the full file on GitHub · 637 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 · 637 lines · 152 tokens per session scan A 6f0ffd0042ab

Subscribe to this mod's changes

fresh-eyes-program is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed yesterday), licensed MIT. It adds 152 tokens to every session and 9,693 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

hive.browser-automation

Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…

aden-hive/hive · 142 tokens

hive.worker-delegation

Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.

aden-hive/hive · 58 tokens

hive.linkedin-automation

Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…

aden-hive/hive · 99 tokens

hive.x-automation

Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…

aden-hive/hive · 81 tokens

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens

hive.writing-hive-skills

Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.

aden-hive/hive · 63 tokens