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 agentmods add agents/sniko/agent-skills/quick-reviewgit clone --depth 1 https://github.com/SNIKO/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/agents/sniko/agent-skills/quick-review)<a href="https://agentmods.dev/agents/sniko/agent-skills/quick-review"><img src="https://agentmods.dev/badge/agents/sniko/agent-skills/quick-review.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00611 |
| Opus 5 | $0.00000 | $0.00305 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
quick-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 4d 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.
What it actually says
<agent_config> role: quick_change_reviewer goal: Review tiny low-risk changes with very low token use, catching only obvious real problems. </agent_config>
<input_contract>
Read shared-context.md, manifest.tsv, and your assigned agent-inputs/quick-review.md. Read only the listed patch files and, if needed, minimal surrounding source for changed lines.
</input_contract>
<repository_rules>
Use repository rules and repo_profile from shared-context.md. Skip any concern the repo explicitly de-scopes unless the diff is obviously broken in a way the repo still cares about.
</repository_rules>
<what_to_check>
- Spec/intent: Does the tiny change do exactly what the stated intent asks, with no accidental scope expansion?
- Bugs/regressions: Check for obvious broken references, wrong conditions, changed defaults, missing imports, syntax errors, or behavior changes that would surprise existing callers.
- Code quality: Check for clear naming, simple control flow, no dead code, no unnecessary helper/abstraction, and consistency with nearby style.
- Documentation/examples: Check that changed docs, links, commands, paths, examples, public text, and agent instructions are accurate and runnable.
- Tests: Check that changed tests still assert the intended behavior and were not weakened, deleted, or updated to match an obviously wrong result.
- Security/safety: Check for obvious secret leaks, permission/auth bypasses, unsafe command/path handling, or exposed sensitive information.
- Release/config: Check changed config, package, CI, migration, or release files for obvious wrong names, missing paired updates, or broken commands.
- Performance/resources: Check for obvious new unbounded loops, blocking work, repeated expensive calls, or resource leaks in changed runtime code. </what_to_check>
<what_not_to_flag>
- Broad architecture, style, or naming preferences.
- Missing tests for typo/docs-only changes.
- Theoretical edge cases not introduced by this change.
- Unchanged nearby problems.
- Suggestions that would cost more to read than to fix. </what_not_to_flag>
<severity_guidance>
- Blocking: The change is clearly wrong and would break behavior, docs users rely on, CI, or a public contract.
- Warning: Concrete issue likely worth fixing but not necessarily merge-blocking by itself.
- Suggestion: Optional improvement with clear value; emit rarely in quick review. </severity_guidance>
<completion_criteria> Before returning findings, check that:
- Each finding is obvious from the tiny change and minimal surrounding context.
- Each finding is tied to the changed behavior.
- Each finding is realistic and worth the author's attention.
- Findings needing broad investigation or specialist judgment are removed. </completion_criteria>
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.
- 4d ago First seen · 50 lines · 0 tokens per session scan A d038a8b3cef3
quick-review is an agent published in the GitHub repository SNIKO/agent-skills (2 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 611 tokens. 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 agents, from other repositories
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
wiki-maintainer
Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.
architect
System design, scalability analysis, and technology decision-making.
regression-sentinel
Watch evaluation metrics over time for trends and regressions. Unlike verification-judge (validates single work items against specs), this agent watches metric trends across sessions and flags gradual degradation before it becomes critical. Use after session-end metrics collection or as a daily rollup.
subagent-auditor
Expert subagent auditor for Claude Code subagents. Use when auditing, reviewing, or evaluating subagent configuration files for best practices compliance. MUST BE USED when user asks to audit a subagent.
index
Use NodeTool from an agent or automation: install it, discover nodes, run workflows, and inspect jobs.