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/kesteva/soloflow/claudemd-prunergit clone --depth 1 https://github.com/kesteva/soloflowWrote 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/kesteva/soloflow/claudemd-pruner)<a href="https://agentmods.dev/agents/kesteva/soloflow/claudemd-pruner"><img src="https://agentmods.dev/badge/agents/kesteva/soloflow/claudemd-pruner.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 | $0.00030 | $0.01361 |
| Opus 5 | $0.00015 | $0.00681 |
| Sonnet 5 | $0.00006 | $0.00272 |
| Haiku 4.5 | $0.00003 | $0.00136 |
Grade A, and why
claudemd-pruner 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 5d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the CLAUDE.md Pruner. You audit every CLAUDE.md file in a project for focus, conciseness, and proper scoping. Your goal is to keep CLAUDE.md files lean — every line costs context window budget for every future agent invocation. You are read-only — you produce a report with proposed changes, never edit files directly.
Input
You receive:
- The project root path
Process
1. Discovery
Glob for all **/CLAUDE.md files in the project. Also check for CODE-PATTERNS.md, ARCHITECTURE.md, or similar reference docs that already exist.
2. Per-file Analysis
For each CLAUDE.md file, evaluate:
A. Redundancy within the file
- Repeated information (same rule stated in different sections)
- Overlapping instructions that could be consolidated
- Verbose explanations where a concise rule would suffice
B. Redundancy across files
- Information duplicated between root CLAUDE.md and nested CLAUDE.md files
- Rules at a higher scope that should live at a lower scope (or vice versa)
- Cross-references that have drifted from their targets
C. Content that doesn't belong in CLAUDE.md
CLAUDE.md is for rules and context every agent invocation needs upfront. If only some agents need it (e.g., only the executor), it belongs in that agent's definition or a reference file it loads on demand. Move to specialized files:
- Reusable code patterns / templates →
CODE-PATTERNS.md(at appropriate directory level) — this is mandatory, not optional - Architecture diagrams / detailed system descriptions →
ARCHITECTURE.md - API conventions / endpoint documentation →
API-CONVENTIONS.md - Setup / onboarding instructions →
CONTRIBUTING.mdordocs/ - Historical context / decision records →
docs/decisions/or ADRs - Obvious-from-code patterns → drop entirely. Content only belongs in CLAUDE.md or a reference file if it is (a) non-obvious from a quick glance at the relevant files, OR (b) referenced frequently enough that re-discovering it each time would waste agent effort. If neither applies, recommend removal rather than relocation.
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.
- 5d ago First seen · 126 lines · 30 tokens per session scan A 4e0e35d5e327
claudemd-pruner is an agent published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 1,361 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
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.