Borrowing it
Nothing to install: this file belongs to JDArmy/Evasion-SubAgents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JDArmy/Evasion-SubAgents/main/.claude/commands/tools_evasion.mdgit clone --depth 1 https://github.com/JDArmy/Evasion-SubAgentsWrote 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/commands/jdarmy/evasion-subagents/tools_evasion)<a href="https://agentmods.dev/commands/jdarmy/evasion-subagents/tools_evasion"><img src="https://agentmods.dev/badge/commands/jdarmy/evasion-subagents/tools_evasion.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 | $0.00026 | $0.00870 |
| Opus 5 | $0.00013 | $0.00435 |
| Sonnet 5 | $0.00005 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
tools_evasion 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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- tools_evasion — 100% identical, 0 lines differ
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 tasked with analyzing a penetration testing tool and modifying its source code to evade detection.
Input
Tool Path: {{tool_path}}
Workflow
Follow these phases in order:
Phase 1: Tool Understanding
- Read README and documentation files
- Analyze source code structure
- Identify programming language and build system
- Determine tool purpose and use cases
- Create tool profile at
rules/{tool_name}/tool_profile.md
Phase 2: Open Source Detection (if applicable)
- Check if the tool is open source
- Extract keywords (name, author, features)
- Search GitHub for tool-specific detection rules
- Save found rules to
rules/{tool_name}/yara/,rules/{tool_name}/sigma/, etc.
Phase 3: Behavior Analysis
- Analyze source code for core behavior patterns:
- Network behavior (HTTP headers, URLs, ports)
- Process behavior (creation, injection)
- File behavior (paths, operations)
- API usage patterns
- String constants
- Extract behavioral signatures
- Search for behavior-based detection rules
- Save found rules
Phase 4: Rule Collection
- Organize all found rules
- Create rule inventory at
rules/{tool_name}/rule_inventory.md - Categorize by type (YARA, Sigma, Network, etc.)
Phase 5: Per-Rule Analysis
For EACH detection rule found:
- Parse all patterns (strings, hex, regex)
- Identify pattern sources in the tool code
- Develop evasion strategies (prioritize compiler flags)
- Create analysis file at
rules/{tool_name}/rule_analysis/{rule_name}.md
Phase 6: Source Modification
CRITICAL: Directly modify source files using Edit tool.
- FIRST: Try build configuration changes (compiler flags)
- SECOND: Apply source code modifications if needed
- Create tasks for each modification
- Verify each change
Modification priority:
- Compiler flags (lowest effort, highest impact)
- Build configuration
- String obfuscation
- API obfuscation
- Function rename
- Behavior change (last resort)
Phase 7: Verification & Summary
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.
- 7d ago First seen · 126 lines · 0 tokens per session scan A 03c49cddb08c
tools_evasion is a command published in the GitHub repository JDArmy/Evasion-SubAgents (315 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 870 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.