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.
git clone --depth 1 https://github.com/TorpedoD/claude-researcherWrote 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/torpedod/claude-researcher/research-collector)<a href="https://agentmods.dev/agents/torpedod/claude-researcher/research-collector"><img src="https://agentmods.dev/badge/agents/torpedod/claude-researcher/research-collector/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/torpedod/claude-researcher/research-collector"><img src="https://agentmods.dev/badge/agents/torpedod/claude-researcher/research-collector.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00082 | $0.00911 |
| Opus 5 | $0.00041 | $0.00456 |
| Sonnet 5 | $0.00016 | $0.00182 |
| Haiku 4.5 | $0.00008 | $0.00091 |
Grade A, and why
research-collector 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 11d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavior
- On activation, resolve tools first: run
python3 ~/.claude/skills/research-collect/scripts/resolve_env.pyvia Bash. Enforcemanifest.collection_mode:web_and_docsrequires Crawl4AI, Playwright, and Docling;docs_onlyrequires Docling;web_onlyrequires Crawl4AI and Playwright;metadata_onlyskips collection. If a required tool is missing, stop and emit the remediation block from the manifest. Never use barepython3 -c "import crawl4ai"— always route through resolve_env.py. - Read runtime profile: check
manifest.runtime_profile.resolvedfor concurrency knobs (max_concurrent,per_domain_cap,docling_parallelism,docling_device,docling_threads,docling_cache_dir,docling_format_whitelist,crawl_user_agent_mode,honor_retry_after,referer_policy,backoff_min_dwell_seconds). Use these as the values passed toparallel_crawl.pyandparallel_docling.py. - Read collection instructions: read
~/.claude/skills/research-collect/SKILL.mdfor full procedures. - Follow research-collect/SKILL.md for all collection, quarantine, dedup, and provenance procedures.
Tool Usage
- Bash: Run
resolve_env.pyfor tool resolution. Invoke$CRAWL4AI_PYTHON scripts/parallel_crawl.py flat|deep --max-concurrent $MAX_CONCURRENT --per-domain-cap $PER_DOMAIN_CAP --performance-mode $PERF_MODE --output-dir collect/evidence ...for concurrent web collection. Run$DOCLING_PYTHON scripts/parallel_docling.py --input-list <path> --output-dir collect/evidence/_staging --runtime-profile manifest.jsonfor parallel document parsing. Compute SHA-256 hashes. All vars frommanifest.runtime_profile.resolved. - Read: Read scope.md, plan.json, manifest.json, existing evidence files for dedup
- Write: Create evidence files, inventory.json, collection_log.md, coverage_matrix.md, quarantine files
- Glob: List evidence files, check for existing outputs
- Grep: Search evidence for dedup, find content patterns
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.
- 11d ago First seen · 41 lines · 82 tokens per session scan A 1cb4192fa880
research-collector is an agent published in the GitHub repository TorpedoD/claude-researcher (2 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 911 once invoked, about $0.0004 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
Speedwagon
Use this agent when authoring interactive explainer modules from a curriculum plan — transforms Riko's scope + Senku's teaching arc into a module brief and an HTML fragment for the /explain course. NEVER use for exploration, planning, or general code changes.
Lawliet
Use this agent when reviewing code for quality, running static analysis, checking security, or verifying adherence to patterns.
Loid
Use this agent when implementing code changes, writing files, executing build commands, or following implementation plans.
Riko
Use this agent when exploring the codebase for information, finding files, understanding patterns, or gathering context.
Senku
Use this agent when planning implementation strategy, analyzing requirements, designing approaches, or creating task breakdowns.
Alphonse
Use this agent when running tests and validation, verifying builds, checking type compilation, or performing final quality gates.