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-data-analysisnpx skills add evoelsewhere/evoflux --skill work-data-analysisgit 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 | $0.00073 | $0.00535 |
| Opus 5 | $0.00036 | $0.00267 |
| Sonnet 5 | $0.00015 | $0.00107 |
| Haiku 4.5 | $0.00007 | $0.00053 |
Grade A, and why
work-data-analysis 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.
Analyze work data
Anchor analysis to a decision and make every material transformation reproducible. A polished chart cannot rescue an undefined population or broken join. Do not load bundled references when this skill activates.
Frame the analysis
- Define the decision, audience, population, unit of analysis, time window, comparison, metrics, and required deliverable.
- Distinguish metric definitions supplied by the user from definitions you infer. Surface decisions about cohort, attribution, time zone, currency, units, denominator, and exclusions.
- Record data provenance and freshness before calculating.
Audit before interpreting
Inspect schema, types, keys, cardinality, duplicates, missingness, coverage, units, time zones, impossible values, and join behavior. Reconcile headline counts or totals to a trusted baseline when one exists.
Read references/data-quality-gates.md only when joining sources, excluding rows, treating outliers, analyzing experiments, forecasting, or resolving a mismatch with a reported metric.
Never silently coerce invalid values, drop duplicates, discard outliers, impute missing fields, or switch denominators. Preserve a compact audit trail of each consequential transformation.
Analyze proportionately
Start with counts, distributions, and denominators. Segment only where it can change the decision. Quantify uncertainty and test alternative reasonable definitions that could reverse the conclusion.
For experiments, check assignment, sample ratio, exposure, pre-period balance, multiple comparisons, and practical—not only statistical—significance. For forecasts, separate observed inputs, model assumptions, scenarios, and error range. Do not imply causation from observational correlation.
Produce the artifact
Create the smallest table or visualization that makes the decision-relevant relationship clear. Keep calculations reproducible in formulas, queries, or code and preserve source data unless transformation is explicitly requested. Protect row-level personal or confidential data in outputs.
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 · 73 tokens per session scan A f301590676ab
work-data-analysis is a skill published in the GitHub repository evoelsewhere/evoflux (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 73 tokens to every session and 535 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
rove
Use when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell. Also the ONLY channel for messaging another agent session on this machine — rove api send, never a peer/MCP side channel.
E2E Testing Nori Skillsets Subcommands
Use when you need to interactively test a nori-skillsets CLI subcommand end-to-end via tmux, with full filesystem isolation.
changelog-generator
Draft Rove release notes as Changesets. Writes user-facing entries as .changeset/.md files for @sma1lboy/rove (consumed into packages/kobe/CHANGELOG.md at release time). Use when the user asks for "changelog", "release notes", "what changed", "add a changeset", or before cutting a version. Enforces Rove's no-soft-wrap…
token-saver-config
Configure and diagnose token-saver compression settings. Use when the user asks about adjusting compression levels, checking processor status, debugging hook issues, or reviewing savings statistics.
issue-review
Triage a copperhead GitHub issue, attempt reproduction, and check it against the spec. Use when the user asks to review an issue, e.g. /issue-review 42 or /issue-review .
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…