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 Sudhakaran88/solopreneur-skills --skill abm-saasgit clone --depth 1 https://github.com/Sudhakaran88/solopreneur-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/sudhakaran88/solopreneur-skills/abm-saas)<a href="https://agentmods.dev/skills/sudhakaran88/solopreneur-skills/abm-saas"><img src="https://agentmods.dev/badge/skills/sudhakaran88/solopreneur-skills/abm-saas/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/sudhakaran88/solopreneur-skills/abm-saas"><img src="https://agentmods.dev/badge/skills/sudhakaran88/solopreneur-skills/abm-saas.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 | $0.00086 | $0.04121 |
| Opus 5 | $0.00043 | $0.02060 |
| Sonnet 5 | $0.00017 | $0.00824 |
| Haiku 4.5 | $0.00009 | $0.00412 |
Grade A, and why
abm-saas 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 12d 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an ABM strategist helping SaaS solopreneurs run focused account-based campaigns against a short list of high-value targets — the approach that makes every dollar of marketing spend accountable.
When to Use ABM
ABM is not for everyone. Use it when three conditions are true simultaneously:
1. ACV threshold — above $5,000 ARR per account Below this, the economics don't work. ABM requires real time investment per account. At $1,200 ACV, you'd need dozens of deals to justify even a modest ABM motion. At $10k–$50k ACV, a single closed account more than pays for the whole campaign.
2. Target accounts are identifiable before they come to you If you can answer "I know the 50 companies I want as customers — by name" then ABM is viable. If your best customers could come from anywhere (SMBs, any industry, any size), inbound or broad outbound serves you better.
3. Sales cycle is longer than 30 days with multiple stakeholders ABM is a multi-touch, multi-channel, relationship-building motion. For transactional or self-serve SaaS, it's overkill. ABM pays off when deals involve procurement, IT sign-off, or executive buy-in — where staying visible across months matters.
Signs you are NOT ready for ABM:
- You don't have a working ICP yet
- You've closed fewer than 10 customers
- Your ACV is under $3k
- You can't name your target accounts from memory
Context Check
Before building anything, answer these five questions:
- What is your current ACV (average contract value)?
- Can you name 20–100 specific companies you want as customers?
- What is your typical sales cycle length?
- Do you have any existing customers who can anchor your ICP?
- What is your monthly time budget for ABM? (Realistic: 5–10 hours/week minimum for 1-to-few)
If ACV is under $5k or you can't answer question 2, redirect to the cold-email skill first.
ABM vs Outbound vs Inbound
These are not competing strategies. They solve different problems.
| Dimension | Inbound | Cold Outbound | ABM |
|---|---|---|---|
| Who initiates | Prospect finds you | You find anyone who fits ICP | You target named accounts specifically |
| Account selection | Whoever shows up | Filtered list, but broad | Hand-picked named accounts |
| Personalization | Generic | Light personalization | Deep, account-specific |
| Channels | SEO, content, paid | Email, LinkedIn | Email + LinkedIn + ads + content — coordinated |
| Best ACV | Any | $1k–$20k | $5k+ |
| Time to results | 6–18 months | 2–8 weeks | 3–6 months |
| Solo feasibility | High | High | Medium (requires discipline) |
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.
- 12d ago First seen · 326 lines · 86 tokens per session scan A 2fb9e06d5235
abm-saas is a skill published in the GitHub repository Sudhakaran88/solopreneur-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 4,121 once invoked, about $0.0004 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
lint
Audit workspace structural health: stale status, orphan files/folders, unannotated decision supersessions, manifest drift. Read-only; --fix applies safe annotations. Use when the user asks for a health check or whether anything is stale, drifted, or inconsistent, or after session-start's unclean-close warning. Don't…
session-end
Use when closing a Memex session: at the SessionEnd hook, when a session is about to time out, when the hook didn't fire, or to force a clean checkpoint before a long break. Updates memory files, refreshes closets, verifies wikilinks.
upgrade
Upgrades an existing Memex workspace to the current major version in one command. Detects current state (manifest marker, summary-format version, closets coverage) and runs only the needed subset of /memex:resummarize, /memex:reindex, and lint.
consolidate
Sweeps the workspace for drift -- duplicate files, unannotated decision supersessions, orphans, bloated decisions logs -- on a cadence separate from session-end. Read-only by default; --fix applies safe annotations only (never auto-merges files).
reindex
Backfills or rebuilds every hub's CLOSETS.md from scratch, so closets exist immediately instead of accumulating across many session-ends -- for a v1-to-v2 upgrade, a large bulk import, or whenever you want full v2 retrieval quality now.
session-start
Use when opening a Memex session: at the SessionStart hook, after /clear, when resuming after a break, or when context feels stale mid-session. Loads tiered context and outputs a briefing.