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 skills add sandsower/beislid --skill fresh-eyesgit clone --depth 1 https://github.com/sandsower/beislidWrote 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/sandsower/beislid/fresh-eyes)<a href="https://agentmods.dev/skills/sandsower/beislid/fresh-eyes"><img src="https://agentmods.dev/badge/skills/sandsower/beislid/fresh-eyes/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/sandsower/beislid/fresh-eyes"><img src="https://agentmods.dev/badge/skills/sandsower/beislid/fresh-eyes.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 | $0.00072 | $0.01287 |
| Opus 5 | $0.00036 | $0.00643 |
| Sonnet 5 | $0.00014 | $0.00257 |
| Haiku 4.5 | $0.00007 | $0.00129 |
Grade A, and why
fresh-eyes 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 10d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fresh Eyes
Run a final whole-diff review pass with no session-history bias. This is a side-effect-free review primitive that uses the same output contract as review, but with a different posture: look across the entire change set after the obvious iterative fixes are done.
fresh-eyes may read files, inspect diffs, and classify findings. It must not edit files, commit, push, post comments, update tickets, create PRs, or run a fix loop. Callers decide what to do with the findings.
Use this for:
- Final pre-PR review from
ready-for-reviewafter the normalreviewloop - A last-pass review after
rinsehas applied iterative fixes - Checking a supplied patch for cross-file consistency and drift
- Catching baseline issues that hunk-by-hunk review missed
If the repo declares custom lifecycle hooks, read ../lifecycle-hooks.md and honor any phase-boundary hooks before and after fresh-eyes.
Do not use this for:
- The first local diff review — use
review - Interactive walkthroughs — use
walk-the-diff - Fixing review findings — return findings to the caller
- Posting PR comments — use
pr-patrol
Process
1. Establish the input
Accept one of:
- Caller-supplied diff/range/context
- Local git diff against a base branch
- Pasted patch/diff
If reviewing local changes and the caller did not supply a range:
git status --short
gh pr view --json baseRefName,headRefName 2>/dev/null
git merge-base HEAD main # or master / PR base when applicable
git diff <base-sha>...HEAD --stat
git diff <base-sha>...HEAD
If the base is unclear, ask once.
2. Load compact context only
Prefer context supplied by the caller:
- What changed and why
- Ticket/spec/design summary
- Verification already run
- Previous review findings that were fixed or accepted
- matching
break_spec_approved,spec_approved, orblueprint_approvedlatest pointer entries when the ticket uses custom artifact locations
Do not rely on long conversation history. If context is missing, say so and review against general production readiness.
What ships with it
1 file 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.
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.
- 10d ago First seen · 153 lines · 72 tokens per session scan A b38082ed10ce
fresh-eyes is a skill published in the GitHub repository sandsower/beislid (10 stars, last pushed 10d ago), licensed MIT. It adds 72 tokens to every session and 1,287 once invoked, about $0.0004 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…