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 jpeslar1/john-peslar-ai-skills --skill icp-validation-sprintgit clone --depth 1 https://github.com/jpeslar1/john-peslar-ai-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/jpeslar1/john-peslar-ai-skills/icp-validation-sprint)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/icp-validation-sprint"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/icp-validation-sprint/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/jpeslar1/john-peslar-ai-skills/icp-validation-sprint"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/icp-validation-sprint.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 | $0.00055 | $0.01174 |
| Opus 5.5 | $0.00022 | $0.00470 |
| Sonnet 5.5 | $0.00011 | $0.00235 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
icp-validation-sprint 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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ICP Validation in 7 Days
Produce a testable buyer hypothesis and a seven-day field test. Treat a polished persona as a hypothesis until real buyers support it. This sprint lays the groundwork for a 30-day first-meeting goal; research conversations do not automatically count as sales meetings.
Find a buyer the user can serve
Use their delivery skills, past paid work, access to people, preferred channel, constraints, and any interview notes. If several markets are plausible, compare at most three on evidence of pain, funding, reachability, and delivery fit. Select a provisional test with reasons; let the user override the choice. Do not confuse being an AI freelancer with selling to AI freelancers.
Describe the person who pays or authorizes the work, their operating situation, painful workflow, desired result, and likely purchase trigger. For an internal operator, identify the sponsor and budget or resource approval path.
Write: I help [specific buyer] get [concrete outcome] without [unwanted effort or risk].
Make five observable disqualifiers relevant to this buyer. Start from inability to fund, wrong problem, no viable authority path, unreachable channel, and service expectations that do not match budget. Do not reject every multi-person buying process: distinguish a real approval path from an inaccessible buyer. Label a guessed budget threshold as provisional.
Run ten conversations in seven days
Start warm on days 1-2, approach matching buyers on days 3-5, and complete missing conversations and score evidence on days 6-7. Aim for ten distinct people, including five who fit the hypothesis beyond the closest warm circle. Make the calendar fit available access. Ten invitations are not ten conversations. If fewer people respond, report the actual sample and leave the verdict provisional.
Draft a warm invitation and a cold-ish observation plus one question. These are learning conversations. Do not disguise a sales pitch as research.
Useful questions from the deck:
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.
- 1mo ago First seen · 75 lines · 55 tokens per session scan A e3720a733fdf
icp-validation-sprint is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 55 tokens to every session and 1,174 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-09.
icp-validation-sprint compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| icp-validation-sprintjpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 55 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |