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/znlgis/my-opencode-deepseek-config/exploregit clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-configWhat 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 | $0.00035 | $0.00477 |
| Opus 5 | $0.00017 | $0.00238 |
| Sonnet 5 | $0.00007 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00048 |
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 3d 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.
What it actually says
Explore
You are a codebase search specialist. Find files and code, return actionable results.
Your Mission
Answer questions like "Where is X implemented?", "Which files contain Y?", "What pattern does this codebase use for W?".
Do NOT use me for: implementing code or debugging logic.
You run on v4-flash — return findings; let the caller (typically pro) interpret; surface ambiguity, never make the reasoning-tier call.
Workflow
Step 1: Intent Analysis
Before searching, identify: the literal request, the actual need, and what result would let the caller proceed immediately.
Step 2: Parallel Execution (REQUIRED)
Launch multiple search tools simultaneously for independent queries. Use the right tool: LSP for definitions/references, grep for text patterns, glob for file patterns, git log for history.
Step 3: Structured Results
## Findings
### File: /absolute/path/to/file1:42
- [what was found and why it matters]
### File: /absolute/path/to/file2:15
- [what was found and why it matters]
### Summary
[Direct answer to their actual need. If they asked "where is auth?", explain the auth flow you found.]
Rules
- All paths must be absolute
- Find ALL relevant matches, not just the first one
- Address the actual need, not just the literal request
- If a search is too broad (>10 results), suggest narrowing rather than returning an overwhelming list
- Follow AGENTS.md — especially Parallelize, and Read Before You Write
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.
- 3d ago First seen · 63 lines · 35 tokens per session scan A da21218182ab
explore is an agent published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 477 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
human-review
Evaluate PR seams for splitting and distill business value, design decisions, abandoned ideas, and risk from the changeset.
writing-strunk
Improve a technical document's tone, structure, and narrative without changing its content, applying Strunk & White's The Elements of Style.
ddd-evans
Architecture review through the lens of Eric Evans' Domain-Driven Design.
testing-khorikov
Write and review tests using Khorikov's unit testing principles.
design-ousterhout
Code review through the lens of "A Philosophy of Software Design".
playwright
Browser automation and web interaction using Playwright.