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 post-disco-followupgit 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/post-disco-followup)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/post-disco-followup"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/post-disco-followup/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/post-disco-followup"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/post-disco-followup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Excessive Agency · line 87 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Memory Poisoning · line 136 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 | $0.00221 | $0.02752 |
| Opus 5 | $0.00111 | $0.01376 |
| Sonnet 5 | $0.00044 | $0.00550 |
| Haiku 4.5 | $0.00022 | $0.00275 |
Grade A, and why
post-disco-followup 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post-Discovery Follow-Up
You produce the post-call follow-up package for a sales discovery call. Every artifact is a DRAFT: never send the proposal, never send the email, never push to a protected branch. The final step is always a confirmation summary so the user can review and send.
This skill is offer-agnostic, backend-agnostic, and process-agnostic. Every business-specific value lives in config/ at the project root. What it produces, and whether a proposal is even part of this touch, is driven by the user's sales process in config. Read config first, then act.
Read config before anything else
Config lives at the project root in config/:
config/offer.md: your offer, identity, delivery channels, theprocessblock (where the proposal sits), theassetsblock (your own templates), qualification, confirmation, output dir, autonomy.config/pandadoc.md: only ifproposal.backendispandadoc.
If config/offer.md is missing or only *.example.md files exist, the user has not run setup. Tell them to run setup-post-disco first, and stop.
If a Context/ folder (offer.md, sales-process.md, config.md) exists in or above the working directory, the user is inside a Sales OS. Read it as the source of truth alongside config/, and write outputs and deal updates per the vault's conventions.
From config, determine up front:
proposal.backend:pandadoc|google_docs|reuse_existing|none- if pandadoc,
proposal.pandadoc.transport:connectororapi email.backend:gmail_connector|gws|noneassets.proposal_template: ifhave_it, you fill THEIR template, not the generic one- the
processblock (next section)
Decide what to produce (process-aware)
Before drafting, decide which artifacts this touch calls for, from the process block and which call in the sequence this is. This is the core of the skill: not every follow-up includes a proposal.
- Determine the call stage. Is this the first discovery call or a later one? In vault mode, read the deal's history. In manual mode, infer from the transcript (introductions and discovery signal a first call) and, if unsure, ask. A routine passes or infers the stage.
- Apply
process.proposal_timing:
What ships with it
10 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.
- assets/examples/email-recap-example.md 1.6 KB
- assets/examples/proposal-example.md 5.6 KB
- assets/templates/email-recap-template.md 1.7 KB
- assets/templates/proposal-template.md 4.1 KB
- references/confirmation-format.md 2.3 KB
- references/email-format.md 4.0 KB
- references/extraction-checklist.md 2.9 KB
- references/google-docs-backend.md 2.7 KB
- references/pandadoc-backend.md 4.0 KB
- references/workflow-rules.md 4.6 KB
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 · 139 lines · 221 tokens per session scan A 9c65e8dee3d5
post-disco-followup is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed yesterday), licensed MIT. It adds 221 tokens to every session and 2,752 once invoked, about $0.0011 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.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.