Agent skill
cost-before-credits
Estimate Clay and enrichment spend before running a table at scale.
Filed under Prospecting and list building.
From rasulshaikh/outbound-skill-pack · 7 skill entries · 0 · pushed 2026-09-29
What it does when it runs
Estimate Clay and enrichment spend before running a table at scale. Use after the column contract and before live enrichment.
Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- No third-party host appears in the skill or its bundled files.
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It only issues instructions, so there is nothing to bound. - Actions present in the files
- None. Instructions only.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/rasulshaikh/outbound-skill-pack.git /tmp/outbound-skill-pack git -C /tmp/outbound-skill-pack sparse-checkout set "skills/cost-before-credits" mkdir -p ~/.claude/skills/cost-before-credits cp -R "/tmp/outbound-skill-pack/skills/cost-before-credits/." ~/.claude/skills/cost-before-credits/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗Reproduced in full from rasulshaikh/outbound-skill-pack/blob/9516d4bfa03b15648816760032ec8035370ca9f4/skills/cost-before-credits/SKILL.md, which is licensed MIT (repository). 226 words, 7 headings.
Cost Before Credits
Price the run before you burn the wallet.
When to use
- Column contract drafted
- Row count known or hypothesized
- Multiple paid enrichers on the path
Process
- List every paid step from the contract (
credit_cost> 0). - Note provider unit price (credits or USD). If unknown, mark
UNKNOWNand block scale-up. - Compute:
- cost_per_row = sum of paid steps that run for a typical qualified row
- qualified_rate hypothesis (e.g. 40% of seeds pass ICP)
- expected_cost = seeds * paths through each step (account for early exits)
- Add a 15% buffer for retries and waterfall fallbacks.
- Compare to campaign budget. If over, propose cuts: fewer seeds, cheaper waterfall, tighter qualify-before-enrich.
Output format
## Cost sheet
| Step | Provider | Unit cost | Rows expected | Line total |
| --- | --- | --- | --- | --- |
| ... | ... | ... | ... | ... |
Subtotal: ...
Buffer 15%: ...
**Expected total: ...**
Budget: ...
Status: UNDER | OVER | UNKNOWN
## Cut options if OVER
1. ...
Guardrails
- Do not recommend running full enrichment when unit costs are UNKNOWN.
- Separate "research sample" cost (10 to 50 rows) from full-list cost.
- Revisit this sheet when the column contract changes.
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- credits-quotas-plans by clay-run · 129
- workflows-optimize-credits by clay-run · 129
- linkedin-cost-monitor by Ad-Superpowers · 5
- shipping-cost-analysis by sidchaudhary · 3
- cost-per-acquisition by sidchaudhary · 3
- cost-optimizer by richapiai · 0
- crm-enrichment-cost-estimate by jurjen-gtm-engineer · 0
- tam-data-cost-estimate by jurjen-gtm-engineer · 0
Need help setting it up?
This page tells you what cost-before-credits does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.