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 skills/evoelsewhere/evoflux/work-researchnpx skills add evoelsewhere/evoflux --skill work-researchgit clone --depth 1 https://github.com/evoelsewhere/evofluxWhat 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 | $0.00074 | $0.00533 |
| Opus 5 | $0.00037 | $0.00267 |
| Sonnet 5 | $0.00015 | $0.00107 |
| Haiku 4.5 | $0.00007 | $0.00053 |
Grade A, and why
work-research 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 2d 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.
Research a work question
Produce a source-governed answer to a decision-relevant question. More links do not automatically create more confidence. Do not load bundled references when this skill activates.
Define the research contract
- State the question, decision or action it supports, audience, geography, time boundary, required depth, and acceptable source types.
- Split the question into the fewest independent subquestions that cover the outcome. Define what would count as enough evidence for each.
- Identify freshness-sensitive claims before searching. Use exact dates and versions where “current,” “latest,” or policy status matters.
Gather evidence
Prefer primary sources: official documentation, laws and regulators, original research, filings, standards, first-party product material, and direct data. Use secondary sources for discovery, independent interpretation, or when the primary source is unavailable. Account for source incentives and methodology.
Maintain a compact evidence ledger with claim, source, publication/update date, scope, and confidence. Read references/source-governance.md for source ranking, contradiction handling, and citation checks when claims are contested, freshness-sensitive, consequential, or based on estimates.
Seek corroboration for material claims only when independence improves confidence. Ten articles repeating one press release remain one source.
Resolve and synthesize
Resolve apparent contradictions by version, date, population, geography, definitions, methodology, and incentives. Do not average incompatible numbers or hide disagreement in vague prose.
Stop collecting when each material subquestion is answered, explicitly unknown, or blocked by inaccessible evidence. Separate:
- confirmed source facts;
- reasoned inference with its premises;
- estimates and their methodology;
- unresolved disagreement or missing evidence.
Verify that every citation opens to the intended source and supports the exact claim attached to it. Quote only when the wording itself matters. Never fabricate a URL, author, date, access result, or publication detail.
What ships with it
3 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.
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.
- 2d ago First seen · 60 lines · 74 tokens per session scan A 5c1ab9936487
work-research is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 74 tokens to every session and 533 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 skills, from other repositories
kane-cli
Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assurance), parse NDJSON output, inspect logs, save runnable test.md. Use for any task requiring a real browser (navigate…
control-chrome
Control the user's Chrome browser for tasks that depend on existing Chrome state: tabs, logged-in sessions, or extensions. Prefer purpose-built connectors, APIs, or CLIs when available.
yutori-computer-use
Run local Mac desktop tasks with Yutori computer use. Use when the user wants to operate macOS apps, websites in a local browser, or cross-app workflows on the visible desktop.
vibesurfer
Agent-native headless browser. 20 primitives over a Unix-socket wire protocol. Real WKWebView (macOS), WebKitGTK 6 (Linux), or WebView2 (Windows) — all three engines CI-verified by 48 integration cells per platform. Optimistic concurrency via state tokens; tree-delta wire format; durable session/page/auth state in…
yutori-research
Execute deep web research on any topic using Yutori's research agents. Use for competitive analysis, market research, finding documentation, or answering complex questions that require synthesizing information from multiple sources.
yutori-browse
Automate browser tasks like form filling, data extraction, or multi-step web workflows. Use when the user needs to interact with websites that require clicking, typing, or navigation.