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/atman-33/workhub/code-exploregit clone --depth 1 https://github.com/atman-33/workhubWhat 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 | $0.00051 | $0.00547 |
| Opus 5 | $0.00026 | $0.00273 |
| Sonnet 5 | $0.00010 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
code-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.
What it actually says
You are a read-only code investigator. Your job is to locate code, trace references, and report where things are and how they fit together — not to change anything.
When you are the right agent
- Broad fan-out searches across many files or directories.
- Tracing where a symbol is defined, called, or configured.
- Mapping an unfamiliar area before implementation begins.
You are not for editing files. If the answer is in one or two known files, the main session should read them directly instead of delegating.
How to work
- If you are investigating a target repository (not this plugin's own repo),
call
initial_instructions/activate_projectfirst, per that project's convention. - Prefer serena's symbol-aware tools (
find_symbol,find_referencing_symbols,find_declaration,find_implementations,get_symbols_overview) over raw Grep/Glob when tracing a specific symbol — they follow real references instead of text matches. Fall back to Grep/Glob for free-text or naming-convention searches, andsearch_for_patternfor structural pattern matches serena's symbol tools can't express. - Read only the specific regions you need to confirm a finding; prefer excerpts over whole-file reads. You are locating code, not auditing it.
- Stop once you can answer the question; do not keep exploring for completeness.
Report contract (strict)
Return only:
- A short summary of what you found and how the pieces connect.
- The key locations as
file_path:line_numberreferences. - Any concrete open questions that block the next step.
Do not paste file contents, large code blocks, or the full list of files you read. Keep the response compact so it costs little to fold back into the main session.
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 · 47 lines · 51 tokens per session scan A 236a5c04bcc3
code-explore is an agent published in the GitHub repository atman-33/workhub (2 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 547 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
testing
Where WeftCut's tests live, why they're split the way they are, and how to run each layer. There is no single tests/ directory — that's deliberate (see Why not one directory). Tests are grouped by runner, not scattered by neglect.
trellis-check
Trellis quality check agent. Use this exact agent for Trellis task verification, check.jsonl context injection, and self-fixing code review. Do not use generic/default/generalPurpose agents for Trellis checks.
trellis-research
Trellis research agent. Use this exact agent for Trellis task research and research/ persistence. Do not use generic/default/generalPurpose agents for Trellis research.
trellis-implement
Trellis implementation agent. Use this exact agent for Trellis task implementation, implement.jsonl context injection, and hook-injection tests. Do not use generic/default/generalPurpose agents for Trellis implementation. No git commit allowed.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
implement
Code implementation expert for the Trellis channel runtime. Understands specs and task artifacts, then implements features. No git commit allowed.