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 magnus919/hermes-profiles --skill researcher-workflowgit clone --depth 1 https://github.com/magnus919/hermes-profilesWrote 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/magnus919/hermes-profiles/researcher-workflow)<a href="https://agentmods.dev/skills/magnus919/hermes-profiles/researcher-workflow"><img src="https://agentmods.dev/badge/skills/magnus919/hermes-profiles/researcher-workflow/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/magnus919/hermes-profiles/researcher-workflow"><img src="https://agentmods.dev/badge/skills/magnus919/hermes-profiles/researcher-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.00963 |
| Opus 5 | $0.00037 | $0.00481 |
| Sonnet 5 | $0.00015 | $0.00193 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade A, and why
researcher-workflow 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 12d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researcher Workflow
A 5-phase workflow for systematic deep research with progressive disclosure artifact output. Designed for the researcher specialist subagent profile when dispatched by an orchestrator.
RECEIVE MISSION → GATHER → EVALUATE GAPS → [RECURSE] → BUILD PYRAMID → DELIVER
Sub-Skills
| Phase | Skill | Trigger |
|---|---|---|
| Receive Mission | researcher-workflow/receive-mission |
Orchestrator assigns a research brief — reformulate into explicit scope |
| Gather | researcher-workflow/research-gather |
Execute research using groktocrawl suite exclusively |
| Evaluate Gaps | researcher-workflow/evaluate-gaps |
Assess gathered material, decide on recursion depth |
| Build Pyramid | researcher-workflow/build-pyramid |
Assemble progressive disclosure artifact files |
| Deliver | researcher-workflow/deliver-findings |
Report back with absolute path references and layer descriptions |
Navigation
When this umbrella is loaded (by the researcher profile), identify which phase you're in, load the corresponding sub-skill via skill_view(), and follow its instructions. Each sub-skill documents its transition signals.
Pipeline Heuristics
- Entry: Always starts at Phase 1 (Receive Mission). The other phases cannot be entered directly.
- Recursion: Phase 3 (Evaluate Gaps) can loop back to Phase 2 (Gather) for targeted follow-up. This is the only non-linear path.
- Tool discipline: ALL web research goes through groktocrawl. The built-in web_search and web_extract tools are explicitly prohibited — they are insufficient and often broken. See references/tool-governance.md for the full fallback chain and rationale. Load with skill_view(name="researcher-workflow", file_path="references/tool-governance.md").
- Artifacts: Output is written to /tmp/researcher-workflow// as layered markdown files. Each layer links downward with descriptions so consuming agents can choose their depth.
- State: No persistent state between phases. Each sub-skill reads the mission brief and artifact directory to determine context.
What ships with it
11 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.
- AGENTS.md 951 B
- decision-map.md 2.0 KB
- manifest.yaml 1.5 KB
- README.md 1.3 KB
- references/generated-from.md 631 B
- references/tool-governance.md 1.3 KB
- skills/build-pyramid.md 4.1 KB
- skills/deliver-findings.md 2.7 KB
- skills/evaluate-gaps.md 3.5 KB
- skills/receive-mission.md 3.1 KB
- skills/research-gather.md 4.2 KB
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.
- 12d ago First seen · 60 lines · 75 tokens per session scan A 04936b026b17
researcher-workflow is a skill published in the GitHub repository magnus919/hermes-profiles (169 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 963 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…