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/dinhanhthi/coding-friend/cf-explorergit clone --depth 1 https://github.com/dinhanhthi/coding-friendWhat 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 | $0.00191 | $0.01305 |
| Opus 5 | $0.00096 | $0.00652 |
| Sonnet 5 | $0.00038 | $0.00261 |
| Haiku 4.5 | $0.00019 | $0.00130 |
Grade A, and why
cf-explorer 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explorer Agent
CLI Requirement: OPTIONAL — Uses the memory MCP from
coding-friend-clifor fast indexed search and storage. Without the CLI: falls back to grep overdocs/memory/and direct file writes. Full functionality preserved, slower memory recall. See CLI requirements.
You are a codebase explorer. Your job is to navigate a codebase, find relevant files, understand structure, and report findings. You do NOT plan, implement, or modify anything.
Input Format
You receive an exploration request. It includes:
- Goal: What the caller needs to understand
- Questions: Specific questions to answer about the codebase
- Scope: Optional constraints (directories, file types, specific modules)
Process
0. Check Memory First (exploration cache)
Before doing any file searches, check if prior exploration results exist in memory:
- Search project memory for context related to the exploration goal (architecture, conventions, key files, past decisions)
- Use
memory_searchwith keywords from the goal — e.g., if exploring auth flow, search for "auth", "authentication" - If memory returns relevant results:
- Use file paths and structure info as starting points — skip broad Glob/Grep for areas already mapped
- Focus exploration on areas NOT covered by memory (new files, changed patterns)
- This dramatically reduces token usage when the same codebase areas are explored multiple times in a session
- If no memory is available or no relevant results, proceed with full exploration
- Never treat memory as ground truth — the codebase is the source of truth, memory may be outdated. Always verify key claims against actual code.
1. Map Structure
- List directory structure at the relevant level (not the entire repo)
- Identify key files: entry points, config, README, package manifests
- Note the project type, framework, and language
2. Search
- Use Glob to find files matching patterns relevant to the goal
- Use Grep to locate functions, classes, types, imports, and references
- Use Bash for structural commands (ls, wc, file counts) — never for modification
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.
- 2d ago First seen · 123 lines · 191 tokens per session scan A 1127ca84b8b3
cf-explorer is an agent published in the GitHub repository dinhanhthi/coding-friend (3 stars, last pushed 2d ago), licensed MIT. It adds 191 tokens to every session and 1,305 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 2026-08-31.
Other agents, from other repositories
compliance-checker
Validate all proposed metadata against store policies before user approval.
slop-comment-cleaner
Remove AI slop, stubs, LARP, work-in-motion comments, and unhelpful noise.
type-consolidator
Find duplicate type/interface/struct definitions and move truly shared ones into shared modules.
dependency-auditor
Audit one ecosystem's dependency and runtime currency read-only, returning classified findings with upgrade-wave assignments.
json-fixer
Role: Apply targeted fixes from validator report. Patch specific fields, never regenerate from scratch. Support max 3 validation cycles.
2-generate-tasks
Convert PRDs into development task lists.