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 skills add TorpedoD/claude-researcher --skill researchgit 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/skills/torpedod/claude-researcher/research)<a href="https://agentmods.dev/skills/torpedod/claude-researcher/research"><img src="https://agentmods.dev/badge/skills/torpedod/claude-researcher/research/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/skills/torpedod/claude-researcher/research"><img src="https://agentmods.dev/badge/skills/torpedod/claude-researcher/research.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 | $0.00033 | $0.12206 |
| Opus 5 | $0.00016 | $0.06103 |
| Sonnet 5 | $0.00007 | $0.02441 |
| Haiku 4.5 | $0.00003 | $0.01221 |
Grade A, and why
research scanned grade A with 1 finding 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 10d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run(["python3", str(script), "--target=raw", str(target)], capture_output=True, text=True) How it starts
The opening of the file, as written. The whole thing — 999 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Orchestrator
Accepts a freeform research request, plans scope, manages a 7-phase claim-based pipeline with 4 human checkpoint gates, and produces a polished, citation-rich research document. Every claim is traceable to its source, every gap is detected and addressed, and every run is reproducible and auditable.
The orchestrator coordinates collection, claim extraction, graph relationship enrichment, section brief synthesis, report composition, and optional publishing. output/report.md is the canonical final report; HTML, PDF, and QMD are publishing products rendered from it.
Claim Pipeline Contract
New runs use manifest.pipeline_contract_version = "claim_pipeline_v1" and these phases:
planning
→ collection
→ claim_extraction
→ graph_relationships
→ section_brief_synthesis
→ formatting
→ publishing
synthesis/claim_bank.json is the canonical research state. synthesis/raw_research.md is deprecated; if a prose diagnostic is needed, write synthesis/research_notes.md and keep it out of the main handoff.
A global file is tiny only when it is under 20KB or under 300 lines. Downstream agents must not read full claim_bank.json, full inventory.json, full graph files, or all section briefs unless the file qualifies as tiny. Otherwise they consume per-section slices.
Dependency install policy
The research pipeline must NEVER auto-install or auto-download these runtime dependencies:
crawl4ai(and its Playwright/browser runtime)playwright/ Playwright browsersdocling
If any of these are missing when the pipeline needs them, the skill/agent MUST:
- Detect the missing dependency.
- Emit a clear message naming the missing tool and the install command the user can run themselves (e.g.,
pipx install crawl4ai,pipx install docling,playwright install chromium). - Stop the run — halt the phase with a non-zero exit. Do NOT proceed with a fallback collection mode.
Never execute pip install, pipx install, npm install, playwright install, crawl4ai-setup, crawl4ai-doctor --install, or any equivalent install command for these tools from within the pipeline.
What ships with it
55 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/architecture_execution_plan.md 4.2 KB
- references/checkpoint_protocol.md 9.9 KB
- references/content_rules.md 6.0 KB
- references/graph_report.contract.md 2.7 KB
- references/graph.json.contract.md 2.7 KB
- references/plan.json.contract.md 3.7 KB
- references/plan.schema.json 3.1 KB
- references/quarto-pdf-base.yml 945 B
- references/question_tree.json.contract.md 6.0 KB
- references/question_tree.schema.json 2.8 KB
- references/run_directory_schema.md 7.2 KB
- references/scope.md.contract.md 2.6 KB
- scripts/build_graph.py 4.1 KB runs code
- scripts/check_content_rules.py 15 KB runs code
- scripts/gate1_validator.py 5.5 KB runs code
- scripts/graph_postprocess.py 4.5 KB runs code
- scripts/init_run.py 26 KB runs code
- scripts/make_qmd.py 1.6 KB runs code
- scripts/publish.sh 4.5 KB runs code
- scripts/question_tree.py 3.9 KB runs code
- scripts/scope_paths.py 910 B runs code
- scripts/validate_artifact.py 3.4 KB runs code
- tests/fixtures/clean_report.md 913 B
- tests/fixtures/contracts/assembly_plan/invalid_missing_required.json 497 B
- tests/fixtures/contracts/assembly_plan/valid_minimal.json 544 B
- tests/fixtures/contracts/claim_bank/invalid_missing_required.json 439 B
- tests/fixtures/contracts/claim_bank/valid_minimal.json 480 B
- tests/fixtures/contracts/claim_graph_map/invalid_missing_required.json 164 B
- tests/fixtures/contracts/claim_graph_map/valid_minimal.json 229 B
- tests/fixtures/contracts/claim_slice/invalid_missing_required.json 188 B
- tests/fixtures/contracts/claim_slice/valid_minimal.json 919 B
- tests/fixtures/contracts/entity_index/invalid_missing_required.json 21 B
- tests/fixtures/contracts/entity_index/valid_minimal.json 286 B
- tests/fixtures/contracts/formatter_audit/invalid_missing_required.json 122 B
- tests/fixtures/contracts/formatter_audit/valid_minimal.json 169 B
- tests/fixtures/contracts/global_id_registry/invalid_missing_required.json 222 B
- tests/fixtures/contracts/global_id_registry/valid_minimal.json 332 B
- tests/fixtures/contracts/section_brief/invalid_missing_required.json 212 B
- tests/fixtures/contracts/section_brief/valid_minimal.json 273 B
- tests/fixtures/contracts/section_graph_hints/invalid_missing_required.json 147 B
- tests/fixtures/contracts/section_graph_hints/valid_minimal.json 488 B
- tests/fixtures/contracts/section_meta/invalid_missing_required.json 184 B
- tests/fixtures/contracts/section_meta/valid_minimal.json 205 B
- tests/fixtures/fence_isolation.md 279 B
- tests/fixtures/merm01_at_limit.md 382 B
- tests/fixtures/merm01_over.md 520 B
- tests/fixtures/rule02_section_refs.md 550 B
- tests/fixtures/violations.md 5.0 KB
- tests/test_claim_pipeline_contracts.py 5.1 KB runs code
- tests/test_claim_pipeline_runtime.py 13 KB runs code
- tests/test_collection_document_links.py 2.6 KB runs code
- tests/test_content_rules.py 7.6 KB runs code
- tests/test_init_run_resume.py 11 KB runs code
- tests/test_legacy_instruction_guard.py 2.1 KB runs code
- tests/test_report_composition_runtime.py 16 KB runs code
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.
- 10d ago First seen · 999 lines · 33 tokens per session scan A 38f13eca1abf
research is a skill published in the GitHub repository TorpedoD/claude-researcher (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 12,206 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.