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.
curl -O https://raw.githubusercontent.com/zkysar1/Claude-Mind/main/.claude/skills/fresh-eyes-tree/SKILL.mdgit clone --depth 1 https://github.com/zkysar1/Claude-MindWrote 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/zkysar1/claude-mind/fresh-eyes-tree)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/fresh-eyes-tree"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/fresh-eyes-tree/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.
<a href="https://agentmods.dev/skills/zkysar1/claude-mind/fresh-eyes-tree"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/fresh-eyes-tree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00161 | $0.10414 |
| Opus 5 | $0.00081 | $0.05207 |
| Sonnet 5 | $0.00032 | $0.02083 |
| Haiku 4.5 | $0.00016 | $0.01041 |
Grade A, and why
fresh-eyes-tree 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 715 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fresh-eyes-tree — Periodic Tree-Taxonomy Self-Audit
Every 200 completed goals (or on user demand), step back and produce a taxonomy assessment:
Are the L1s still the right top-level cuts for the knowledge tree?
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 via git log and tracked signals.
If taxonomy changes are desired, the user can invoke the S8 apply scripts
(l1-domain-rename.sh, l1-domain-add.sh) manually. These scripts remain
standalone user-runnable tools. The periodic ritual does NOT auto-invoke or
gate on them.
Sibling Relationship
Third sibling in the fresh-eyes ritual family. All three 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 |
/fresh-eyes-tree |
Knowledge-tree top-level taxonomy | 200 goals | last_fresh_eyes_tree_review |
Lower frequency (200 vs 100 vs 25) because L1 changes are high-blast-radius and the evidence needs accumulation time. Skew + pick-rate signal is most useful when measured across a few hundred goals.
Sub-commands
/fresh-eyes-tree — User-forced review, bypasses cadence gate
/fresh-eyes-tree --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_tree
# 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-tree: 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_tree_review --claim
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.
- 12d ago First seen · 715 lines · 161 tokens per session scan A 3b32f2c73c72
fresh-eyes-tree is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed yesterday), licensed MIT. It adds 161 tokens to every session and 10,414 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.
Other skills, from other repositories
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
learning-capture
Log corrections, errors, and discoveries to orbital/LESSONS.md so future sessions avoid repeating mistakes.
obsidian
A skill for working with an Obsidian vault, which is a folder of Markdown notes used as a personal knowledge base. It covers creating, extending, searching, and organizing notes, including links, tags, folders, and daily entries.
mupeng-sync
Propagate Mupengism values and knowledge to new agents. Deploy AGENT-VALUES.md, onboard new subagents with core principles. The missionary skill.