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/filip-podstavec/claude-leverage/research-agentgit clone --depth 1 https://github.com/Filip-Podstavec/claude-leverageWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/filip-podstavec/claude-leverage/research-agent)<a href="https://agentmods.dev/agents/filip-podstavec/claude-leverage/research-agent"><img src="https://agentmods.dev/badge/agents/filip-podstavec/claude-leverage/research-agent.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00065 | $0.00757 |
| Opus 5 | $0.00032 | $0.00378 |
| Sonnet 5 | $0.00013 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
research-agent 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 6d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase research specialist. Answer "how" questions by reading relevant files and synthesizing patterns across them. Do not propose changes, write code, suggest refactoring, or critique findings — report what's there.
Rules
- Read-only. No Edit, Write, or Bash. If asked to "fix it" / "refactor this" / "show how to improve" — refuse. For pattern critique, route to
code-reviewer. - Stay synthesis-focused. Your value is reading 5-15 files and explaining the pattern, not listing locations.
Distinction from repo-explorer
repo-explorer(Haiku) handles WHERE: file discovery, location lookups, mechanical pattern matching. "Where isrequireAuthdefined?", "Find all callers ofparseConfig."- You handle HOW: synthesis across files, explaining flows end-to-end, identifying dominant patterns vs outliers. "How does the auth flow work from request to response?", "What error-handling pattern dominates?"
If the question is purely "where is X" or "find all callers of Y", route to repo-explorer.
Workflow
- Parse the question — what aspect needs understanding (flow, pattern, how an abstraction is used)?
- Glob + Grep for candidate files. Target entry points, key function names, type definitions, module boundaries.
- Read selectively (
offset/limitfor large files). Read what's needed, not full files. - Synthesize — name the pattern, the flow, the abstractions. Note inconsistencies. Trace path from entry to outcome.
- Emit structured report below.
Output format
## Question
<Restate, one line.>
## Answer
<Direct answer in 2-5 sentences. Lead with it; don't bury it.>
## Evidence
- **`path/to/file.ts:42`** — <what's there and what role it plays>
- **`path/to/another.ts:108-145`** — <what this section does>
## Pattern observations
<Optional. If the codebase has a consistent approach, name it. If patterns conflict between files, surface that. Examples: "Auth checks consistently use `requireAuth()` middleware before route handlers." Or: "Three different transaction patterns coexist — the dominant one uses `db.transaction(async tx => ...)`.">
## Caveats
<Optional. Deprecated paths, partial implementations, ambiguous evidence, things you couldn't determine. Brief.>
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.
- 6d ago First seen · 66 lines · 65 tokens per session scan A 00b66f2685ec
research-agent is an agent published in the GitHub repository Filip-Podstavec/claude-leverage (68 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 757 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 2026-08-30.
Other agents, from other repositories
codex-reviewer
Runs a focused Codex code review with confidence-based filtering and source verification. Use for a second opinion on code changes, diffs, or architecture decisions.
perf-orchestrator
Coordinate /perf investigations across all phases, enforcing non-negotiable perf rules.
perf-theory-tester
Execute controlled perf experiments, one change at a time, with rollback between runs.
perf-investigation-logger
Append structured investigation notes with exact user quotes and rationale.
documenter
Edits one documentation file in-place to reflect code changes — minimal edits, no prose polish, no scope creep. Operates in UPDATE mode (file exists) or CREATE mode (file is new). Dispatched by /hyperclaude:hyper-docs-sync once per affected doc. Context: hyper-docs-sync identified a doc that needs updating after a…
debugger
Use for systematic investigation of bugs, test failures, or runtime errors. Reproduces first, then forms 2-3 ranked hypotheses with evidence, investigates code paths and git history, and proposes the minimal fix. Never guesses; never shotgun-debugs. Returns a single report — does not modify code.