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 lemur47/logic --skill evmgit clone --depth 1 https://github.com/lemur47/logicWrote 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/lemur47/logic/evm)<a href="https://agentmods.dev/skills/lemur47/logic/evm"><img src="https://agentmods.dev/badge/skills/lemur47/logic/evm/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/lemur47/logic/evm"><img src="https://agentmods.dev/badge/skills/lemur47/logic/evm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.04012 |
| Opus 5.5 | $0.00000 | $0.01605 |
| Sonnet 5.5 | $0.00000 | $0.00802 |
| Haiku 4.5 | $0.00000 | $0.00401 |
Grade A, and why
evm 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 1mo 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 — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EVM: Earned Value Management for Project Health Tracking
Source: github.com/lemur47/logic
Purpose
Help users answer one question: "Are we on track?" using Earned Value Management metrics. This skill replaces gut-feel status reporting and traffic-light dashboards with four computed numbers (SV, SPI, CV, CPI) that tell you exactly where a project stands — in schedule and in budget — at any point in time.
EVM is the performance counterpart to PERT. PERT asks "how long will it take?" before the project starts. EVM asks "are we on track?" once it's running.
When to Use
- Mid-project health checks ("we're 3 months in, are we OK?")
- Sponsor/steering committee reporting with actual data
- Detecting schedule or cost problems before they become crises
- Evaluating whether 人海戦術 (adding headcount) is helping or hurting
- Deciding whether to re-baseline, descope, or extend the deadline
- Any situation where someone says "I think we're roughly on track"
Terminology — The 4 Inputs
EVM has four inputs. Everything else is computed. Never confuse input with output.
| Abbr | Full Name | What It Means | Who Provides It |
|---|---|---|---|
| BAC | Budget at Completion | Total planned budget for the entire project | Set once at baseline, frozen |
| PV | Planned Value | How much work should be done by now, in budget terms | Derived from schedule: BAC × (% of schedule elapsed) |
| EV | Earned Value | How much work is actually done, valued at planned rates | Sum of (planned cost of each completed deliverable × its % complete) |
| AC | Actual Cost | What was actually spent on the work performed | From accounting, timesheets, or invoices |
Critical distinction: EV is not what was spent. EV is the planned budget for the work that's been completed. If a $10,000 deliverable is 50% done, EV = $5,000 regardless of whether you actually spent $3,000 or $8,000 on it.
PV shortcut (linear assumption): If you don't have a detailed planned-value curve, use: PV = BAC × (months elapsed / total months). This assumes work is evenly distributed — good enough for most conversational health checks.
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.
- 1mo ago First seen · 328 lines · 0 tokens per session scan A c323cac756f6
evm is a skill published in the GitHub repository lemur47/logic (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,012 tokens. 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
Linear
Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.
arrows-crm-hygiene
CRM guide and hygiene check from Sales Skills by Arrows. Learns how the person's CRM and pipeline really work (the stages, how deals move and where they stall, which fields to update after each call) and saves it as a guide every Sales Skill can use. Then checks the CRM against it: past close dates, no next step…
arrows-process-gaps-report
Arrows process gaps report: finds what's falling through the cracks in your pipeline, measured against your own sales process. Part 1 is what should be happening and isn't: promised follow-ups that never went out, deals quiet 14+ days with money at stake, missing next steps, single-threaded deals, no economic buyer…
metagit-projects
Ongoing workspace and project management for OpenClaw and Hermes agents. Use when starting work, organizing repos, or before creating a new project folder so existing metagit projects are reused instead of duplicated.
metagit-control-center
Use when running metagit as an MCP control center for multi-repo awareness, guarded sync, and operational knowledge across ongoing agent tasks.
metagit-rewrite-campaign
Orchestrate a reference-implementation rewrite across source and target repos using campaigns, parity registry conventions, objectives, and subagent handoffs.