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 avizmarlon/agent-skills --skill impact-metrics-gategit clone --depth 1 https://github.com/avizmarlon/agent-skillsWrote 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/avizmarlon/agent-skills/impact-metrics-gate)<a href="https://agentmods.dev/skills/avizmarlon/agent-skills/impact-metrics-gate"><img src="https://agentmods.dev/badge/skills/avizmarlon/agent-skills/impact-metrics-gate/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/avizmarlon/agent-skills/impact-metrics-gate"><img src="https://agentmods.dev/badge/skills/avizmarlon/agent-skills/impact-metrics-gate.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 | $0.00033 | $0.01217 |
| Opus 5 | $0.00016 | $0.00609 |
| Sonnet 5 | $0.00007 | $0.00243 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
impact-metrics-gate 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 11d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Impact Metrics Gate — Measure Before Building
Core Principle
Every project, feature, or solution must define its impact metrics before development begins. The impact of any deliverable should be expressible in a single sentence that a non-technical stakeholder can understand.
If you cannot define impact in one clear sentence, the project is not yet ready to build.
Mandatory Gate Before Build
| Item | What It Is | Example |
|---|---|---|
| Primary impact metric (quantifiable) | The single, most important measurement of success. Must be a number. | "Reduce average task completion time from 45 min to 20 min" / "Increase monthly recurring revenue by $5k" / "Achieve 80% test coverage" |
| Measurement method (source + collection) | Where the data comes from and how it is collected. Be specific about tooling and frequency. | "Timestamp delta in task tracking API, 7-day rolling average" / "Payment processor dashboard, monthly export" / "Code coverage tool CI report" |
| Baseline or benchmark (starting point) | The current state or competitive reference point. Do not leave this as "zero" if measurable data exists. | "Current: 45 min (measured week of 2026-01-15)" / "Baseline: $0 MRR" / "Competitor average: 60% coverage" |
Where to Document
- New projects: Include an "Impact Metrics" section in the specification document, README, or charter. Place it before any implementation begins.
- Features in existing projects: Add the metrics section to the feature specification.
- Projects without a spec: Create at least the Impact Metrics section before starting development.
Retroactive application: Projects already in progress without defined metrics should add this section during the next development session. Do not block ongoing work, but make the gap visible in session handoff or progress documents.
Anti-Patterns (Blocked)
| Anti-Pattern | Why It Fails | Fix |
|---|---|---|
| "Improves user experience" (no number) | Immeasurable. Improves how much? For whom? | Define the metric: "Reduces task time by X%", "Increases satisfaction score from Y to Z" |
| Metric without method | Theater. If you cannot measure it, it is not a metric. | Specify exact source, tool, and collection frequency. |
| "Baseline: zero" when current state exists | Lazy. Measure the before. | Run a 1-week baseline before build and record it. |
| Build without any metric defined | Waste. You cannot verify impact after launch. | Define metric + method + baseline. This is mandatory, not optional. |
| Metric that depends on future data you cannot collect | Impossible to validate. | Ensure the metric is observable before you ship. |
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.
- 11d ago First seen · 93 lines · 33 tokens per session scan A bf0ec2e8d11e
impact-metrics-gate is a skill published in the GitHub repository avizmarlon/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,217 once invoked, about $0.0002 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
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
content-engine
Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.