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 s977043/river-review --skill context-budget-tuninggit clone --depth 1 https://github.com/s977043/river-reviewWrote 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/s977043/river-review/context-budget-tuning)<a href="https://agentmods.dev/skills/s977043/river-review/context-budget-tuning"><img src="https://agentmods.dev/badge/skills/s977043/river-review/context-budget-tuning/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/s977043/river-review/context-budget-tuning"><img src="https://agentmods.dev/badge/skills/s977043/river-review/context-budget-tuning.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 | $0.00045 | $0.01867 |
| Opus 5 | $0.00023 | $0.00933 |
| Sonnet 5 | $0.00009 | $0.00373 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade A, and why
Context Budget Tuning 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 8d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern declaration
Primary pattern: Reviewer
Secondary patterns: Tool Wrapper
Why: .river-review の context 設定変更時に、reviewMode プリセット選択 / token・char 上限 / ranking weights をモデル仕様と照合してレビューする educator スキル。
Goal / 目的
.river-review.{yaml,json}のcontext.reviewMode/context.budget/context.ranking変更が モデル仕様 (model.modelName) と整合しているか をレビューで確認する。reviewMode: tiny | medium | largeプリセットの 既定値 (1024 / 4000 / 16000 max tokens) と explicitbudgetの優先関係を理解させる。- ranking weights (
pathProximity/symbolUsage/siblingTest/commitRecency) の 0.0〜1.0 範囲 とスキーマキー名を schema (src/config/schema.mjs) と照合する。
Guidance
reviewMode プリセット既定値 (src/lib/context-presets.mjs)
| reviewMode | maxTokens 既定 | 想定モデル |
|---|---|---|
tiny |
1024 | コンテキスト窓の小さいモデル / 短い PR |
medium |
4000 | gpt-4o-mini / sonnet 級モデルの通常 PR |
large |
16000 | 大型モデルでの深掘りレビュー |
- 明示的
context.budgetがある場合は 常に preset より優先 する。 budget.maxTokensの上限は schema で64000、maxCharsは200000まで。
モデル仕様との整合チェック
context.budget.maxTokensは 使用するmodel.modelNameの公式仕様(または運用上採用している実効 context window) を超えないように設定する。プロバイダの仕様変更で値は変動するため、本スキルでは具体値を固定しない。- 小型モデル(例:
gpt-4o-mini級)にlargeプリセット (16000 token) を当てると、モデルの実効 context window を超える分は切捨てられて redundant になり、コストのみ増える。プリセットの maxTokens がモデル仕様の上限を上回らないか を確認する。 - 逆に大型モデルに
tinyプリセット (1024 token) を当てている場合は、context が不足してレビュー品質が落ちる可能性を指摘する。
ranking weights のレビュー
- キーは schema 定義 (
pathProximity/symbolUsage/siblingTest/commitRecency) と一致しなければならない。古い名称(symbolOverlap/testAffinity)は #728 で廃止済み。 contextRankingSchema.weightsは.strict()のため、未知キーを含む設定は 設定ロード時に Unknown key エラーで失敗 する(silently 無視されない)。古い名称が残っている設定は CI でも気付かれず動き続けることはなく、即座に明示的なエラーになる。- 各 weight は
0.0〜1.0。合計が 1 を超えても問題ないが、scoreContextCandidateが weighted average を取るため相対比のみが意味を持つ。
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.
- 8d ago First seen · 121 lines · 45 tokens per session scan A 8778e6e3ec01
Context Budget Tuning is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,867 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 2026-09-03.
Other skills, from other repositories
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
logic-health
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…
omnicheck-gitlab
Use when checking if MR review findings have been applied — verifies both OmniForge-generated and human reviewer comments against the current diff, posts nudge replies on unaddressed threads.
omnicheck-github
Use when checking if PR review findings have been applied — verifies both OmniForge-generated and human reviewer comments against the current diff, posts nudge replies on unaddressed threads.
omnicreate-gitlab
Use when creating a GitLab merge request (OmniForge). Auto-populates title and description from commits, supports draft MRs, labels, assignees, reviewers, and issue linking.
logic-diff
Compare two code versions for semantic equivalence via semi-formal tracing of both versions side-by-side. Trigger when the user shares a refactor, rewrite, migration, or A/B implementation and wants to confirm behavior is unchanged — "did I break anything", "is this equivalent", "are these equivalent", "semantically…