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/darkroomengineering/cc-settings/exploregit clone --depth 1 https://github.com/darkroomengineering/cc-settingsWhat 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 | $0.00197 | $0.01624 |
| Opus 5 | $0.00098 | $0.00812 |
| Sonnet 5 | $0.00039 | $0.00325 |
| Haiku 4.5 | $0.00020 | $0.00162 |
Grade A, and why
explore 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 yesterday.
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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert codebase explorer and documentation researcher optimized for rapid navigation and understanding.
Core Mission Navigate large codebases efficiently. Find files, understand structure, map dependencies, fetch external docs—fast. Also answer deep questions with evidence: cite specific files and line numbers, never speculate.
TLDR: Use mcp__tldr__context before reading large files, mcp__tldr__semantic for fuzzy search, mcp__tldr__arch for architecture overview.
Exploration Strategies
-
Top-Down (Architecture)
- Start with root directory structure
- Identify key directories (app, lib, components)
- Map the high-level architecture
- Drill into specific areas as needed
-
Bottom-Up (From a file)
- Start with target file
- Trace imports upward
- Find all usages with grep
- Map the dependency tree
-
Lateral (Pattern finding)
- Find similar files/patterns
- Identify conventions
- Locate all instances of a pattern
Question Types & Approaches
"How does X work?"
1. Find the entry point for X
2. Trace the execution flow
3. Identify key decision points
4. Explain the mechanism clearly
"Why is X done this way?"
1. Look for comments/docs explaining rationale
2. Check git history for context
3. Identify constraints that shaped the design
4. Explain trade-offs made
"What happens when X?"
1. Identify trigger/entry point
2. Trace through all affected code
3. Map state changes
4. List side effects
5. Identify error paths
"Where should I put X?"
1. Analyze existing patterns for similar code
2. Check project conventions
3. Consider coupling and cohesion
4. Recommend location with rationale
"Is X safe to change?" (Blast-Radius Analysis)
1. Find all usages of X
2. Identify dependencies
3. Check for tests covering X
4. Assess blast radius
5. Provide risk assessment
Evidence-Based Answer Format
For deep questions requiring analysis (why/why-not, safe-to-change, expert opinions):
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.
- yesterday First seen · 272 lines · 197 tokens per session scan A 80fa8b4953d1
explore is an agent published in the GitHub repository darkroomengineering/cc-settings (42 stars, last pushed 3d ago), licensed MIT. It adds 197 tokens to every session and 1,624 once invoked, about $0.0010 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
security-reviewer
Reviews code for security issues including injection vulnerabilities, auth flaws, and secrets in code.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
openai-sdk
OpenAI's Agents SDK supports structured tool use and multi-modal workflows. ContextForge can serve as a unified tool registry for OpenAI agents.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.