Borrowing it
Nothing to install: this file belongs to agenticpay-dev/agenticpay. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agenticpay-dev/agenticpay/main/CLAUDE.mdgit clone --depth 1 https://github.com/agenticpay-dev/agenticpayWrote 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/instructions/agenticpay-dev/agenticpay/claude-md)<a href="https://agentmods.dev/instructions/agenticpay-dev/agenticpay/claude-md"><img src="https://agentmods.dev/badge/instructions/agenticpay-dev/agenticpay/claude-md/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/instructions/agenticpay-dev/agenticpay/claude-md"><img src="https://agentmods.dev/badge/instructions/agenticpay-dev/agenticpay/claude-md.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 | $0.00560 | $0.00560 |
| Opus 5.5 | $0.00224 | $0.00224 |
| Sonnet 5.5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
agenticpay CLAUDE.md 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.
What it actually says
agenticpay
Trzy fakty, które kosztowały więcej niż jedno sprawdzenie. Każdy ma czym go obalić, więc nie wierz im na słowo, jeśli coś się nie zgadza.
Merge do main nie wdraża produkcji
Hostowany facilitator na Heroku (agentpay-facilitator) deployuje się ręcznie:
git push heroku main:main. Prod potrafił z tego powodu stać trzy miesiące za
mainem. Sprawdź: heroku releases -n 1 -a agentpay-facilitator i porównaj SHA
z git log -1 main. (2026-09-02)
Brak sieci w /supported bywa poprawny
Facilitator mierzy saldo fee payera i ogłasza tylko sieci, na których faktycznie
zapłaci opłatę. Mainnet jest dziś wstrzymany, bo fee payer ma tam 0 SOL. To nie
jest awaria. Sprawdź: GET / zwraca feePayerReadiness z saldem per sieć, a
logi startowe piszą [fee payer] <sieć>: READY|WITHHELD. (2026-09-02)
Kody odrzucenia z @x402/svm wychodzą na drucie
packages/facilitator/test/svm-scheme-compliance.test.ts przypina je co do
znaku, a /verify zwraca je klientowi. Bump @x402/svm potrafi je przemianować
(2.24.0 dodał prefiks invalid_exact_svm_), więc bump i poprawka testów muszą
wejść jednym commitem. Sprawdź: src/exact/facilitator/errors.ts w paczce.
(2026-09-02)
Alert Dependabota potrafi nie mieć PR-a
Przebieg bezpieczeństwa, który ma otworzyć poprawkę, potrafi się wywrócić i nie
zostawia po sobie śladu ani w liście PR-ów, ani w widoku alertów. Między 08.09 a
13.09.2026 wywróciły się cztery takie przebiegi (hono, @ai-sdk/provider-utils)
i alerty zostały bez poprawki. Sprawdź:
gh run list --limit 25 --json conclusion,displayTitle --jq '.[]|select(.conclusion=="failure")'.
(2026-09-13)
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 Changed · +9 lines · +148 tokens per session 7a09f3cdbe13
- 2mo ago First seen · 27 lines · 412 tokens per session scan A 9470c9b8b86d
agenticpay CLAUDE.md is an instructions file published in the GitHub repository agenticpay-dev/agenticpay (3 stars, last pushed 5d ago), licensed MIT. It adds 560 tokens to every session, about $0.0022 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 2026-09-04.
agenticpay CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agenticpay CLAUDE.mdagenticpay-dev/agenticpay | Instructions file | 3 | 5d ago | MIT | A | 560 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |