--- name: deep-research description: Dispatch exhaustive deep web research to the research profile. Triggered by "deep research", "ask web", or "research this". The research profile runs with the deep-web-research skill loaded — six-move flow, external ledger, mechanical saturation, disconfirmation, condensation from disk. version: 2.2.0 author: Hermes Agent license: MIT platforms: [linux] metadata: hermes: tags: [research, deep-research, delegation, web-search, scraping] related_skills: [ask-hermes, ask-claude, ask-dev, deep-web-research, writing-plans] --- # deep-research — Exhaustive Web Research Delegation ## Overview Dispatches a research question to the research profile, which runs with the `deep-web-research` skill loaded. The research agent does exhaustive, trail-following research — any tool, any trail, no rush — then condenses everything into a tight, concrete, evidence-backed answer. This agent just relays the result. See `references/design-rationale.md` for the v2.0 architecture decisions and Claude validation findings. **Trigger phrases:** "deep research", "ask web", "research this", "deep dive on", "exhaustive research on" ## Clarifying Questions (Before Dispatch) If the operator's question is ambiguous enough that the research agent would waste the first ~20 turns guessing, ask clarifying questions BEFORE dispatching. Cap is tight on purpose — if you find yourself writing more than 5, the question itself is under-specified and the right move is to push back to the operator, not interrogate them. **Limits:** - **Default cap: 3 questions.** Most well-formed questions need 0–3. - **Hard cap: 5 questions.** Only if the question has multiple high-stakes branches that genuinely change the research strategy. - **Abort at 6+:** If you think you need more than 5, the question is under-specified. Stop and tell the operator: "This question has too many branches to dispatch cleanly. Can you narrow it to [specific scope]?" Do NOT fire 6+ questions. **When to ask vs. when to dispatch:** - Ask when the answer would change the research strategy (e.g., "Are you researching a person, a company, or a topic?" — different toolkits). - Do NOT ask when the research agent can sensibly find out (e.g., "What year did X happen?" — the research will find it). - Do NOT ask to delay dispatching. Asking is a cost, not a hedge. **Multi-turn narrowing:** If after 1–2 rounds of clarifying questions the scope is still unclear, abandon the dispatch and ask the operator to rewrite the question with the scope made explicit. Do not loop. ## Command ``` hermes -p research -s deep-web-research chat -q "" -Q --max-turns 600 --yolo ``` - Output line 1: `session_id: ` — capture this - Output line 2+: the research agent's condensed answer - Hold the session_id for follow-up questions **Subsequent asks (resume the session):** ``` hermes -p research -s deep-web-research chat --resume -q "" -Q --max-turns 600 --yolo ``` ## What the Research Agent Does The `deep-web-research` skill on the research profile enforces: 0. **Analyze & Strategize** — analyze the question, select tools from the arsenal, write strategy to ledger 1. **Decompose** — break the question into sub-questions with time classifications 2. **Landscape Pass** — shallow sweep, identify key sources and terms 3. **Deep-Dive** — 3+ search angles per sub-question, full-page reads, citation trails, depth-first 4. **Disconfirmation** — actively hunt for contradiction and outdated claims 5. **Condensation** — read the external findings ledger from disk, synthesize into a concrete answer The research agent writes all findings to `/tmp/research-.md` (external ledger) and uses a phase gate file to enforce completion before condensing. Mechanical saturation checks (`grep -c`) prevent endless searching. Re-strategize checkpoints after Move 2 and every ~10 findings during Move 3 enable mid-research pivots. ## When to Use - User says "deep research", "ask web", "research this", "deep dive on" - Question requires exhaustive multi-source investigation - User wants current, verified, cross-referenced information - Phone number lookup, person research, topic investigation, fact verification ## When NOT to Use - Simple factual question (capital of France, current time) - Question I can answer from a single search - Task that needs my exact context state - User explicitly says "quick search" or "just look it up" ## Relay Rule Relay the research agent's actual response. Do not paraphrase or summarize. If the response is long, chunk it. The research agent already condensed — don't re-condense. ## Spot-check Rule The research agent self-reports are not verified fact. If it claims a file write, `read_file` the path to confirm. If it claims a specific finding, spot-check the source URL. ## Session Persistence **HARD RULE: Same topic = resume. New topic = new session.** - **Same topic / same line of research:** Always `--resume `. Capture session_id from output line 1. Every follow-up in the same line of research MUST use `--resume `. Starting fresh discards the research context and wastes turns. - **New topic / new line of research:** Start a fresh session. Do NOT resume an unrelated session — the research context is polluted with the old topic and will produce confused results. ## Common Pitfalls 1. **Profile flag required.** Always use `-p research`. The sticky default may be general. 2. **Skill flag required.** Always use `-s deep-web-research`. Without it, the research agent runs in normal mode without the methodology. 3. **--yolo is required.** The research agent runs headless. Without it, approval prompts fail closed. 4. **600 turns is the ceiling, not the target.** The research agent should condense well before 600. Hitting the ceiling means it failed to condense. The operator's standing rule: 600 is a safety net, not a budget — "I just want a safety net. I would even be okay with 600 as a catch. I mostly want the job done right. Not concerned with time or tokens." Apply 600 for any plan-building, research, or evidence-based work; default to lower only for short factual lookups. 5. **Don't re-condense.** The research agent already produced a condensed answer. Relay it, don't summarize it further. 6. **Don't do the research yourself.** If the user triggers deep research, dispatch it. Don't run a few searches and call it done. This is the #1 failure mode: the agent runs 2-3 `mcp_searxng_searxng_web_search` calls, gets empty results, and gives up. That's not deep research — that's a casual lookup. If you catch yourself typing `mcp_searxng_searxng_web_search` for a deep research request, STOP. You're doing it wrong. Dispatch to the research profile. 7. **The methodology skill lives on the research profile.** `deep-web-research` is at `~/.hermes/profiles/research/skills/research/deep-web-research/SKILL.md`. It does NOT exist on the general profile. Don't search for it here — it won't be found. The general profile only has this delegation skill. ## Pre-Dispatch Reasoning Check (MANDATORY) Before EVERY deep research dispatch, set the research profile's reasoning_effort to `max`. This is a hard gate — do not dispatch without it. ``` hermes -p research config set agent.reasoning_effort max ``` `max` is the highest effort setting universally supported by all models. No model-specific table needed. If the model changes to one that supports `xhigh`, the user will set it in config — the pre-dispatch check just ensures it's at `max` minimum. ## Research → Validate → Fix Pipeline When the user wants a research deliverable validated and corrected, use this three-stage pipeline: ``` Stage 1: Deep research → produces .md Stage 2: Ask-hermes validation → produces _validation.md Stage 3: Deep research fix pass → updates .md with corrections ``` **Operational guide (exact prompts, session handling, failure modes):** `references/research-validate-fix.md`. The summary below is the quick reference; the reference file is the deep version. **Stage 2 prompt template** (dispatch to `ask-hermes`): ``` Validate the plan at . Read the full file first. CRITICAL: Use mcp_searxng_searxng_web_search for EVERY claim and cite the source URL. Validate: model versions, license claims, VRAM claims, tool availability, new tools since plan was written, hardware benchmarks. For each finding: CLAIM → VERIFIED/CONTRADICTED/UPDATED → source URL → recommended fix. Save to _validation.md. ``` **Stage 3 prompt template** (resume the research session): ``` Read the validation report at _validation.md. Read the current plan at .md. Apply ALL fixes from the validation report. Keep all existing content. Make targeted edits only. Do NOT rewrite the whole plan. ``` **Key rules:** - Stage 2 and 3 can run in parallel with other work (both are background processes). - Stage 3 MUST use `--resume ` from Stage 1 — same research session, same context. - The validation agent (Stage 2) is a fresh `ask-hermes` session each time — no resume needed. - If Stage 2 finds CRITICAL omissions, Stage 3 must address them before the plan is considered complete. - Operator must apply the **Disagreement Scan** (see `ask-hermes` skill) to Stage 2 findings before applying them in Stage 3 — peer findings are input, not commands.