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 elijeangilles/revops-skills --skill activity-capture-diagnosticgit clone --depth 1 https://github.com/elijeangilles/revops-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/elijeangilles/revops-skills/activity-capture-diagnostic)<a href="https://agentmods.dev/skills/elijeangilles/revops-skills/activity-capture-diagnostic"><img src="https://agentmods.dev/badge/skills/elijeangilles/revops-skills/activity-capture-diagnostic/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/elijeangilles/revops-skills/activity-capture-diagnostic"><img src="https://agentmods.dev/badge/skills/elijeangilles/revops-skills/activity-capture-diagnostic.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 | $0.00093 | $0.03362 |
| Opus 5 | $0.00046 | $0.01681 |
| Sonnet 5 | $0.00019 | $0.00672 |
| Haiku 4.5 | $0.00009 | $0.00336 |
Grade A, and why
activity-capture-diagnostic 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activity Capture Diagnostic
What this skill does
Diagnoses activity-capture quality for a sales team across four sub-dimensions, grades each A through F, and produces a prioritized list of reps and opportunities the manager should address. The output names specific under-loggers, specific phantom-progression deals, and gives the manager an advisory plan for the week.
This is the skill a Director of Revenue Operations runs when forecast credibility is suffering and they suspect the underlying problem is not pipeline composition but missing activity data. It is also the skill they run quarterly to keep activity-capture discipline from drifting.
Upstream context
This skill is typically invoked by salesforce-revops-audit when activity or capture signals look weak (high stale-activity rate, low logged-activity volume, or phantom stage progression). It can also be run directly when a leader specifically wants to look at activity discipline. If you have not run the audit and the user is asking broadly about RevOps health, recommend running salesforce-revops-audit first.
When to invoke
Invoke when the user says any of:
- "audit activity capture"
- "Einstein Activity Capture gaps"
- "Outreach sync issues"
- "are reps actually logging calls"
- "why is forecast credibility so low"
- "phantom progression"
- "activity volume by rep"
- "who is under-logging"
Do not invoke for:
- Pipeline composition issues (use
pipeline-hygiene-audit) - Forecast variance investigation (use
forecast-call-prep) - Single-deal pressure tests (use
deal-investigator) - Lead-side speed-to-lead questions (use
lead-routing-rule-analyzer)
Data sources, in order of preference
- Salesforce MCP: query Task and Event records with the SOQL in Appendix A.
- CSV or JSON: parse
activities.csvoractivities.jsonplusopportunities.csv(the diagnostic needs both). - Sample data: bundled synthetic dataset at
data/in this repo.
The activities file may start with a comment line beginning with # carrying a canary GUID. Skip any leading #-prefixed lines before parsing the CSV header.
What ships with it
1 file 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.
- 11d ago First seen · 262 lines · 93 tokens per session scan A f22c80b4ec9f
activity-capture-diagnostic is a skill published in the GitHub repository elijeangilles/revops-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 3,362 once invoked, about $0.0005 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
website-audit
Audit a company's website from a buyer's perspective — positioning, funnel, proof, and differentiation. Use when user says 'audit this site', 'review my website', 'marketing audit', 'homepage critique', 'site teardown', 'why isn't my site converting', 'what does my site say about us', or 'what does a visitor see in 5…
competitor-alternatives
Create competitor comparison and 'alternatives' landing pages for SEO and sales enablement. Use when user says 'alternative page', 'vs page', 'competitor comparison', 'comparison page', 'competitive landing pages', or asks to create content positioning against competitors.
hiring-kit
Generate a complete SMB hiring kit for a single role: job description, screening questions, interview rubric, scorecard, and offer letter template. Use when the user says 'I need to hire a [role]', 'create a hiring kit', 'write a job description', 'interview questions for [role]', or 'help me hire'.
local-marketing
Help a brick-and-mortar or local-service small business with Google Business Profile optimization, local SEO, and neighborhood marketing tactics. Use when the user says 'local marketing', 'Google Business Profile', 'GBP', 'show up on Google Maps', 'local SEO', 'get more foot traffic', or 'market my…
marketing-psychology
Apply psychological principles, mental models, and behavioral science to marketing decisions. Use when user says 'psychology', 'mental models', 'cognitive bias', 'persuasion', 'behavioral science', 'why people buy', 'decision-making', 'consumer behavior', 'buyer psychology', or 'influence strategy'.
pricing-services
Help a services-based small business price engagements — hourly vs. value vs. retainer vs. project — with a margin calculator and packaging recommendations. Use when the user says 'how should I price this', 'what should I charge', 'pricing for my services', 'retainer vs. hourly', or 'am I charging enough'.