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 T4LEL/Claude-Arsenal --skill pitchgit clone --depth 1 https://github.com/T4LEL/Claude-ArsenalWrote 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/t4lel/claude-arsenal/pitch)<a href="https://agentmods.dev/skills/t4lel/claude-arsenal/pitch"><img src="https://agentmods.dev/badge/skills/t4lel/claude-arsenal/pitch/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/t4lel/claude-arsenal/pitch"><img src="https://agentmods.dev/badge/skills/t4lel/claude-arsenal/pitch.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 | $0.00031 | $0.00680 |
| Opus 5 | $0.00015 | $0.00340 |
| Sonnet 5 | $0.00006 | $0.00136 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
pitch 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 10d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pitch
Fundraising and presentation materials that survive due diligence. Every number is sourced from real data or explicitly labeled as an assumption — no exceptions.
Copy this checklist and check off items as you complete them:
Pitch Progress:
- [ ] Step 1: Narrative
- [ ] Step 2: Numbers
- [ ] Step 3: Materials
- [ ] Step 4: Objection prep
- [ ] Step 5: Honesty gate (mandatory)
- [ ] Report
Step 1 — Narrative
Delegate to the biz-strategist agent with the product and market context: the problem, why now, the wedge, moat, and an honest read of the competition. Weak or hand-wavy answers here get flagged, not smoothed over — a shaky narrative should read as shaky in the deck, not be papered over with adjectives.
For the market slide, delegate to the market-analyst agent: TAM/SAM/SOM sized bottom-up with sources and the arithmetic shown — investors check that math first.
Step 2 — Numbers
Delegate to the finance-analyst agent with the real data available: traction to date (real numbers only — never invented), unit economics, and projections. Every projection row gets its assumption labeled inline (growth rate, conversion, churn) so a reader can see exactly what's fact and what's forecast. Also nail down the ask (amount, instrument) and the use of funds.
Step 3 — Materials
Delegate to the copywriter agent with the narrative and numbers: a 10-12 slide deck outline, one message per slide, each headline written as the takeaway sentence (not a topic label). Also produce a one-pager. If final formatted documents are needed, hand off to the docs-writer agent.
Step 4 — Objection prep
Work out the top 5 objections an investor will raise (market size, competition, team gaps, moat, timing) and write honest answers. Anything genuinely unanswerable becomes its own risks slide in the deck — never an omission the investor discovers in diligence.
Step 5 — Honesty gate (mandatory)
Scan every number and claim produced across Steps 1-4 — narrative (market size), numbers, deck/one-pager, and objection answers — no exceptions. Each one is either sourced (cite where — traction dashboard, contract, real usage log) or explicitly labeled an assumption. Any number recalled from memory without a source is an unverified assumption, labeled as such — never presented as fact. This step blocks completion; do not report done until it's finished.
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.
- 10d ago First seen · 51 lines · 31 tokens per session scan A dc8fcdeae247
pitch is a skill published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 680 once invoked, about $0.0002 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
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
annotating-task-lineage
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
aws-cloudformation-cloudfront
Provides AWS CloudFormation patterns for CloudFront distributions, origins (ALB, S3, Lambda@Edge, VPC Origins), CacheBehaviors, Functions, SecurityHeaders, parameters, Outputs and cross-stack references. Use when creating CloudFront distributions with CloudFormation, configuring multiple origins, implementing caching…