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-decisionnpx skills add evoelsewhere/evoflux --skill work-decisiongit 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 | $0.00078 | $0.00511 |
| Opus 5 | $0.00039 | $0.00255 |
| Sonnet 5 | $0.00016 | $0.00102 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
work-decision 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make a work decision
Reduce ambiguity enough for an owner to commit. Do not return an unranked menu or manufacture numeric precision from weak evidence. Do not load bundled references or templates when this skill activates.
Frame the decision
- State the decision in one sentence, decision owner, deadline, success measure, non-negotiable constraints, and scope horizon.
- Separate verified facts, assumptions, preferences, and unknowns. Identify the few unknowns that could reverse the recommendation.
- Define a small set of viable options, including the status quo only when it is genuinely feasible.
Compare options
Evaluate outcome, total cost, time-to-value, risk, reversibility, operating burden, lock-in, opportunity cost, and second-order effects that matter to this decision. Use a weighted matrix only when explicit weights reveal a real priority; show uncertain scores as ranges or qualitative judgments.
Read references/decision-rubric.md only when stakes are high, evidence conflicts, criteria need weighting, or the team is arguing from different time horizons.
Test the leading option against failure scenarios and the strongest argument for alternatives. Distinguish cost of delay from cost of a wrong choice. Prefer an experiment or staged commitment when it can cheaply resolve a decision-changing unknown.
Recommend and commit
Recommend one option. Name:
- decisive evidence and tradeoffs accepted;
- assumptions on which the recommendation depends;
- exact threshold or event that would reverse it;
- smallest next commitment;
- early warning signal, review point, and rollback where applicable.
When the decision needs a durable team record, copy assets/decision-record.md into the deliverable and replace every placeholder. Do not load the template merely to answer a concise question.
Deliverable
Lead with the recommendation and decision status. Follow with decisive evidence, rejected alternatives, uncertainty, reversal condition, and next action. Never invent stakeholder agreement, costs, dates, or authority.
What ships with it
4 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 · 57 lines · 78 tokens per session scan A a47edf6306bf
work-decision is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 78 tokens to every session and 511 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.
recent-release
Render Rove's recent releases as a self-contained, Rove-styled HTML page (Chinese by default). Reads shipped notes from packages/kobe/CHANGELOG.md + git tags, filters to user-facing changes, and emits one standalone .html file in the claude theme (terracotta on near-black, JetBrains Mono, terminal chrome). Use when…
yutori-scout
Set up continuous web monitoring with Yutori Scouts. Use when the user wants to track news, competitors, product updates, funding rounds, price changes, or any recurring web information.
plan-review-triggers
Required reading whenever drafting any multi-step proposal, implementation plan, refactor approach, or response containing file paths and decision points. Use BEFORE writing any response that lists 3+ file paths, 2+ option-tradeoffs, a "Plan:"/"Steps:"/"Concrete changes:" section, or ends with "OK to proceed?" /…
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.