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 a8cteam51/claude-code-plugins --skill fresh-eyes-reviewgit clone --depth 1 https://github.com/a8cteam51/claude-code-pluginsWrote 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/a8cteam51/claude-code-plugins/fresh-eyes-review)<a href="https://agentmods.dev/skills/a8cteam51/claude-code-plugins/fresh-eyes-review"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/fresh-eyes-review/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/a8cteam51/claude-code-plugins/fresh-eyes-review"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/fresh-eyes-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00142 | $0.01417 |
| Opus 5.5 | $0.00057 | $0.00567 |
| Sonnet 5.5 | $0.00028 | $0.00283 |
| Haiku 4.5 | $0.00014 | $0.00142 |
Grade A, and why
fresh-eyes-review 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 2d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fresh-eyes-review
Re-examine a change that was just made, find what was missed, and fix it (the user almost always wants fixes, not just a list). The core stance: distrust your own recent work. The bugs that survive the first pass are the ones you were confident about — re-derive from ground truth instead of re-confirming from memory.
Work the checks below in order. Skip a check only when it's clearly inapplicable, and say so. Don't declare "looks good" until you've actually run the checks — a clean report you didn't earn is worse than no report.
Step 1 — Re-read the real change, not your memory of it
Pull the actual diff against the base, not just the last commit: git diff <base>...HEAD for the whole branch, git diff and git diff --staged for uncommitted work, or gh pr diff <number> for a PR. List every file and hunk that changed. If you're reasoning about what the code does from your mental model, stop and read the bytes. Most missed bugs hide in the gap between "what I meant to write" and "what is actually there."
Step 2 — Audit callers of everything whose contract changed
For every function, method, hook, constant, schema, or return shape whose signature or shape changed, grep for all usages and confirm each one still works:
- A signature that gained/lost/reordered a parameter → every call site updated? A missed one is a latent fatal error or a silently-wrong argument.
- A renamed/removed symbol → no dangling references?
- A changed return shape → every consumer handles the new shape?
Explicitly confirm there are no callers outside the file you edited that you forgot. "I only changed this one function" is exactly when a missed caller bites.
Step 3 — Verify every assumption against ground truth
This is where most real misses live. Anything you guessed rather than confirmed must be checked against the authoritative source — not assumed:
- Identifier / field / enum / operation / tool / API names → check the real API response, schema, type definition, or doc.
- File paths, config keys, constant values → check the real file.
- "It's probably called
x" / "it returns roughly{...}" → go look. If the real name differs, your code silently no-ops or breaks.
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.
- 2d ago First seen · 75 lines · 0 tokens per session scan A b91e090eec00
fresh-eyes-review is a skill published in the GitHub repository a8cteam51/claude-code-plugins (5 stars, last pushed 4d ago), licensed MIT. It adds 142 tokens to every session and 1,417 once invoked, about $0.0006 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 2026-10-24.
Other skills, from other repositories
sync-model-processor
Reviews changes to Chromium Sync model internals in components/sync/model/, including ClientTagBasedDataTypeProcessor, ClientTagBasedRemoteUpdateHandler, ProcessorEntity, ProcessorEntityMetadata, and ProcessorEntityTracker. Use when modifying or reviewing processor state transitions, entity metadata tracking, conflict…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
gsd-ns-review
Invoke this Pi skill with /skill:gsd-ns-review.
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.