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 naveedharri/benai-skills --skill pipeline-reviewgit clone --depth 1 https://github.com/naveedharri/benai-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/naveedharri/benai-skills/pipeline-review)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/pipeline-review"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/pipeline-review/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/naveedharri/benai-skills/pipeline-review"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/pipeline-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 223 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00144 | $0.02288 |
| Opus 5 | $0.00072 | $0.01144 |
| Sonnet 5 | $0.00029 | $0.00458 |
| Haiku 4.5 | $0.00014 | $0.00229 |
Grade A, and why
pipeline-review 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 7d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Review
Pull every prospect from a target pipeline stage, cross-reference their full email history and meeting transcripts, and produce a concise action-oriented summary sent via Slack.
What This Skill Produces
A Slack message (sent to the user or a channel they specify) containing, for each prospect:
- Contact info (email, phone)
- Deal value and pipeline metadata (stage, priority, forecast)
- A 1-3 sentence recap of the sales cycle so far
- Action items from YOUR end (what your team needs to do)
- Action items from THEIR end (what the prospect owes you)
- A clear recommendation: follow up, escalate, or move out of pipeline
The message is concise and skimmable -- no emojis, no walls of text. A busy founder should be able to scan it in under 2 minutes and know exactly what to do today.
Phase 0: Gather Context
Use AskUserQuestion to collect what you need. Combine into 1-2 calls.
Round 1 -- Pipeline & Delivery
Question 1 -- Which pipeline and stage? "Which CRM list/pipeline should I review, and which stage(s) do you want me to focus on?"
- If they don't know the exact list name, use
list-liststo show them the options. - Common stages: "Next Call Scheduled", "Proposal Sent", "Negotiation", "Follow-up Needed"
Question 2 -- Where should I send the summary? "Where do you want the pipeline summary sent? I can DM you on Slack or post it to a channel."
- Default: DM to the user. Search for their Slack user by email from CRM workspace membership.
Round 2 -- Scope (if needed)
Question 3 -- Any prospects to skip? "Should I review ALL prospects in that stage, or skip any?"
- Usually the answer is "all" -- but some users want to exclude recently-added leads or specific names.
After collecting answers, confirm your understanding before pulling data.
Phase 1: Data Collection
Step 1 -- Discover CRM Structure
Read references/CONNECTORS.md for connector-specific patterns. The general flow:
- Find the list: Use
list-lists(Attio) or equivalent to locate the target pipeline - Understand the schema: Use
list-list-attribute-definitionsto identify the stage field slug, deal value field, and other entry-level attributes - Identify record-level fields: Use
list-attribute-definitionson the parent object (usually "people") to understand where email, phone, name live
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.
- 7d ago First seen · 226 lines · 144 tokens per session scan A 8975bc2f3d65
pipeline-review is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed yesterday), licensed MIT. It adds 144 tokens to every session and 2,288 once invoked, about $0.0007 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 2026-09-05.
Other skills, from other repositories
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
collab-pm-report
A Korean-language assistant for creating weekly business review reports. A WBR is a regular meeting or report about results, ongoing work, plans, risks, and decisions.
hr-operations
A skill for designing remote-work and team-operation policies. It covers flexible work, asynchronous communication, collaboration tools, productivity tracking, and employee experience.
hr-performance-review
A skill for designing and running employee performance reviews. It covers MBO, OKRs, KPIs, 360-degree feedback, review guides, and feedback conversations; OKRs set goals and measurable results, while KPIs track ongoing performance.
collab-process
A process-documentation assistant for Korean workplaces. It helps write operating manuals, SOPs, purchasing documents, meeting notes, and action plans; an SOP is a repeatable step-by-step work procedure.
collab-status-report
A reporting skill that turns supplied metrics or existing files into KPI dashboards and weekly, monthly, or quarterly status reports. KPIs are measurable indicators of progress toward a goal; OKRs pair goals with measurable results.