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 PaulRBerg/agent-skills --skill fresh-eyes-sweepgit clone --depth 1 https://github.com/PaulRBerg/agent-skillsWrote 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/paulrberg/agent-skills/fresh-eyes-sweep)<a href="https://agentmods.dev/skills/paulrberg/agent-skills/fresh-eyes-sweep"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/fresh-eyes-sweep/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/paulrberg/agent-skills/fresh-eyes-sweep"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/fresh-eyes-sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Excessive Agency · line 36 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 83 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00054 | $0.04216 |
| Opus 5.5 | $0.00022 | $0.01686 |
| Sonnet 5.5 | $0.00011 | $0.00843 |
| Haiku 4.5 | $0.00005 | $0.00422 |
Grade A, and why
fresh-eyes-sweep 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 17d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fresh Eyes Sweep
If a slash or dollar invocation already added these instructions to the conversation, follow them directly. In that case, do not invoke this skill again through a skill tool.
Inspect the requested Git scope for mistakes supported by evidence. Fix every safe issue. Account for every mapped file. A verified no-op requires that coverage and a full pass that finds nothing new. Leave sound work unchanged. Edits are not required to demonstrate a successful sweep.
--max-runtime DURATION is optional: it is a positive integer followed by m or h, such as 45m or 3h. Reject an
invalid duration, unknown option, or ambiguous positional input. When a deadline is supplied, calculate it before
auditing. In that case, reserve the final 15% for aggregate validation and reporting, clamped to 5–30 minutes and never
exceeding the total runtime. At that window, settle in-flight slices and do not start new fixes. Report an incomplete
sweep with its ledger rather than overrunning the deadline.
Overnight Autonomy
At invocation, read the environment's local time. If it is strictly after 22:00 or strictly before 08:00, treat the entire run as autonomous even if it later crosses a boundary. Exactly 22:00 and 08:00 are outside this window.
During an autonomous overnight run:
- Do not ask the user any questions or pause for clarification, selection, or approval. This does not broaden the skill's authority: leave destructive, disclosure, purchase, public-contract, and other approval-dependent actions undone.
- Use the smallest safe reversible interpretation and continue all independent work. Put every ambiguity, blocked issue, and approval-dependent choice on an overnight backlog instead of interrupting the run.
- Present the backlog at the end with each item's evidence, safe disposition, impact, and decision needed. Phrase the entries as findings, not questions. Omit the section when the backlog is empty.
Ledger Interface
Resolve scripts/sweep-ledger.py from this SKILL.md. Create the scratch ledger outside the repository:
What ships with it
2 files 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.
- 17d ago Changed · +1 lines b1d198e0467a
- 1mo ago Changed · +6 lines 28140500da8f
- 1mo ago Changed · +20 lines · +2 tokens per session 0591fe6ef28d
- 1mo ago Changed · +5 lines · +4 tokens per session 3a7afd911ae3
- 1mo ago Changed · +4 lines 0db4fddb75bd
- 1mo ago Changed · +17 lines 5a150431c642
- 1mo ago Changed · +33 lines · +8 tokens per session bd6f274d52e4
- 1mo ago Changed · +1 lines 79496dfc26ad
- 2mo ago Changed · +15 lines 4085b12231e9
- 2mo ago First seen · 191 lines · 40 tokens per session scan A 924133b79a09
fresh-eyes-sweep is a skill published in the GitHub repository PaulRBerg/agent-skills (104 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 4,216 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
fresh-eyes-sweep compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fresh-eyes-sweepPaulRBerg/agent-skills | Skill | 104 | 2d ago | MIT | A | 54 | Claude Code, Codex |
| sync-bridgechromium/chromium | Skill | 25k | today | BSD-3-Clause | A | 109 | Claude Code, Codex |
| sync-model-processorchromium/chromium | Skill | 25k | today | BSD-3-Clause | A | 98 | Claude Code, Codex |
| adversarial-revieweremdash-cms/emdash | Skill | 14k | today | MIT | A | 72 | Claude Code, Codex |
| gsd-ns-reviewopen-gsd/gsd-core | Skill | 11k | today | MIT | A | 16 | Claude Code |
| gitnexushashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 58 | Codex |
| issuejeremylongshore/tons-of-skills-marketplace | Skill | 2.9k | yesterday | MIT | A | 115 | Claude Code |