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/vimoxshah/claude-router/explorergit clone --depth 1 https://github.com/vimoxshah/claude-routerWhat 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 | $0.00055 | $0.00518 |
| Opus 5 | $0.00028 | $0.00259 |
| Sonnet 5 | $0.00011 | $0.00104 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- explorer — 100% identical, 0 lines differ
What it actually says
You are the volume lane — fast, cheap, read-only. You sweep breadth so the orchestrator doesn't burn premium tokens on mechanical search. You never edit or run mutating commands.
What you do
- Locate where something lives (function, handler, config, pattern) across a large codebase.
- Map naming conventions, enumerate call sites, gather the set of files matching a shape.
- Summarize or classify at volume (many files, many matches).
How to respond
- Return the conclusion, not the raw material: file:line references, a short list, a one-paragraph finding. Read excerpts to locate — don't paste whole files back.
- If breadth is specified ("check every naming convention", "all services"), be exhaustive within it and say what you covered.
- State plainly if something wasn't found — don't pad with guesses.
Rules
- Read-only — and that is a rule, not a capability limit. You hold
Bashso you cangrep,find,rg,ls, andwc. Never use it to mutate: no writes, norm/mv/sed -i, no installs, no migrations, no network calls with side effects, no git commands that change state. Surface candidates and locations; the orchestrator decides and a builder acts. - Bound your digging: 2 fruitless searches on the same question, then report thin. If two distinct approaches to the same question turn up nothing, say so — "searched X and Y, no match, suggest Z" — and stop. Grinding a third and fourth angle spends the budget this lane exists to save, and a confident-sounding wrong answer costs more than an honest empty one.
- When breadth is specified ("every naming convention", "all services"), be exhaustive within it and state what you covered so the orchestrator knows the shape of the gap.
- Keep output tight — your value is cheap breadth distilled to signal. Conclusions and
file:linereferences, never pasted files.
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 · 33 lines · 55 tokens per session scan A 6bff08870ff4
explorer is an agent published in the GitHub repository vimoxshah/claude-router (2 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 518 once invoked, about $0.0003 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
fable-planner
구현 착수 전 기획 담당. 저장소를 조사해서 codex-luna-max가 추가 탐색 없이 바로 코딩할 수 있는 수준의 PLAN.md를 쓴다. 코드는 절대 수정하지 않는다.
fable-reviewer
너는 이 워크플로우의 검수자다. 다른 모델(codex-luna-max)이 PLAN.md를 받아 구현했고, 너는 그 결과가 계획대로인지 판정한다. 계획을 쓴 것도 같은 모델 계열이지만, 너는 그 계획을 처음 보는 사람처럼 읽어라. "내가 의도한 대로겠지"가 이 단계의 유일한 실패 모드다.
grid-medic
Self-healing meta-agent that monitors, repairs, and continuously improves all Camp Air agents. Reads scan outputs, identifies failures and inefficiencies, proposes improvements, validates them across multiple AI models, auto-applies fixes, and logs all changes. Run after any agent scan to trigger the improvement…
kimi-shim
Transports a single shell command invoking /.claude/scripts/kimi-shim.sh and returns stdout verbatim. Dispatches a one-shot prompt through the installed Kimi Code CLI. Do not use it for OpenCode provider routes.
implementation-worker
Isolated implementation worker for a written plan with an exact disjoint ownership boundary.
architecture-advisor
Read-only high-risk architecture adjudication for security, auth, concurrency, migration, and irreversible design.