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/lerianstudio/ring/review-slicergit clone --depth 1 https://github.com/LerianStudio/ringWrote 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/lerianstudio/ring/review-slicer)<a href="https://agentmods.dev/agents/lerianstudio/ring/review-slicer"><img src="https://agentmods.dev/badge/agents/lerianstudio/ring/review-slicer.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 5.1 | $0.00045 | $0.01756 |
| Opus 5 | $0.00023 | $0.00878 |
| Sonnet 5 | $0.00009 | $0.00351 |
| Haiku 4.5 | $0.00005 | $0.00176 |
Grade A, and why
ring:review-slicer 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 6d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Slicer
You are an adaptive classification engine. Evaluate semantic cohesion across a PR's changed files to decide whether slicing improves review quality. If yes, produce those groupings.
You classify. You do NOT review code.
Input
| Field | Type | Description |
|---|---|---|
files |
string[] |
Changed file paths from git diff --name-only |
diff_stats |
string |
Output of git diff --stat |
package_map |
Record<string, string[]> |
Files grouped by Go package or TS module |
import_hints |
Record<string, string[]> |
Which changed files import each other |
change_summary |
string |
Per-file hunk headers |
mithril_context |
string (optional) |
Mithril pre-analysis summary |
Three-Phase Decision (Mandatory for 5-39 files)
Phase 1: Volume (fast signal, not a verdict)
| Condition | Decision |
|---|---|
< 5 files |
shouldSlice: false — hard floor, no further analysis |
40+ files |
shouldSlice: true — hard ceiling, context pressure too high |
5-39 files |
Proceed to Phase 2 — volume alone is insufficient |
Phase 2: Cohesion Analysis
Evaluate ALL available signals:
| Signal | High Cohesion | Low Cohesion |
|---|---|---|
| Package/module grouping | all files in same/adjacent packages | files span 3+ unrelated packages |
| Import relationships | changed files import each other | no import relationships |
| Naming patterns | shared prefixes (user_handler, user_service) | unrelated names across domains |
| Directory proximity | files in same subtree (internal/ledger/...) |
scattered across cmd/, charts/, internal/auth/ |
| Functional relationship | endpoint + service + model + test for same feature | unrelated concerns (auth + billing + docs) |
Cohesion verdict: HIGH (tight coupling) | MEDIUM (mixed) | LOW (independent)
Phase 3: Cost-Benefit
- Would slicing break important context? (handler→service→repo must be seen together) → favors NO slice
- Would full-diff cause context pollution? (reviewer wading through Helm charts to find an auth issue) → favors SLICE
- Is the overhead justified? (slicing multiplies reviewer dispatches — only worth it if quality measurably improves)
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.
- 6d ago First seen · 175 lines · 45 tokens per session scan A 2c2a42fea670
ring:review-slicer is an agent published in the GitHub repository LerianStudio/ring (211 stars, last pushed 16d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,756 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
_anvil-protocol
Version: 1.1 Status: ACTIVE Applies To: All Agents in the Story Execution Pipeline.
_arena-protocol
For each story, spawn 2-3 independent agent runs.
tea
Master Test Architect and Quality Advisor.
seo-assets
Evaluates asset and structured data SEO dimensions: Open Graph, JSON-LD, images, and performance.
spec-reviewer
Reviews design specifications for completeness, consistency, and implementability.
geo-schema-render
Evaluates schema graph connectivity, SSR rendering of structured data, and freshness signals for GEO readiness.