token-efficiency-review

A whole-repository review agent that checks token usage, file length, instruction-file size, and common patterns that waste an AI coding agent’s context.

In plain words
What is it for?
Use it during a full repository review to find oversized files or instructions and decide whether rules should be shortened or procedures moved elsewhere.
Why use it?
It identifies accumulated inefficiency that a review of only the latest code changes may miss.

Agent

Install

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.

agentmods
npx agentmods add agents/bdfinst/agentic-dev-team/token-efficiency-review
Clone the repo
git clone --depth 1 https://github.com/bdfinst/agentic-dev-team
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,188 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.01188
Opus 5 $0.00012 $0.00594
Sonnet 5 $0.00005 $0.00238
Haiku 4.5 $0.00002 $0.00119

Measured 2d ago against content hash 8729c925c195, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

token-efficiency-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.

plugins/dev-team/agents/token-efficiency-review.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implemented by: ${CLAUDE_PLUGIN_ROOT}/scripts/token_efficiency_review.py

Token Efficiency Review

Scope: on-demand Cites: [adversarial-review-protocol] Enforcement: script

Dispatched by the whole-tree /repo-review command, never by /code-review's per-diff panel (#1733). Its findings (file length, CLAUDE.md size, LLM anti-patterns) are properties of absolute size and accumulated drift, not of any single diff's delta — a diff-scoped review of a 20-line PR can't even see a file that crept past a size threshold over 10 separate small PRs. select_lenses.py's resolver reads this Scope: on-demand declaration directly and never selects it for the per-diff roster — the agent body is the single source of truth for this exclusion, same as any other Scope: kind.

Output JSON: per ${CLAUDE_PLUGIN_ROOT}/knowledge/review-agent-output-contract.md (Whole-file load: short, canonical schema).

Status: pass=efficient, warn=optimization opportunities, fail=major waste Severity: error=critical waste, warning=significant, suggestion=minor Confidence: high=mechanical (trim verbose rule, extract procedure to skill); medium=verbosity identified, rewrite depends on intent; none=requires human judgment (what detail level is appropriate)

Context needs: full-file

Skip

Return {"status": "skip", "issues": [], "summary": "No Claude Code config or source files in target"} when:

  • Target has no CLAUDE.md, rules, skills, or source code files
  • Target contains only binary or generated files

Thresholds

Target Limit
CLAUDE.md <5000 chars
Code examples in CLAUDE.md ≤10
Rules ≤200 chars each
Skill definitions ≤2000 chars
File length ≤500 lines
Function length ≤50 lines
Nesting depth ≤5 levels
JSDoc comments ≤15 lines
Commented-out code ≤5 lines total

Findings

Metric thresholds are enforced by ${CLAUDE_PLUGIN_ROOT}/scripts/token_efficiency_review.py (exit 1 for errors, exit 2 for warnings). This agent provides qualitative analysis for issues the script cannot detect mechanically.

Read the full file on GitHub · 140 lines

Changes

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.

  1. 2d ago First seen · 140 lines · 23 tokens per session scan A 8729c925c195

Subscribe to this mod's changes

token-efficiency-review is an agent published in the GitHub repository bdfinst/agentic-dev-team (277 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 1,188 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens