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.
git clone --depth 1 https://github.com/solanabr/solana-ai-kitWrote 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/agents/solanabr/solana-ai-kit/devops-engineer)<a href="https://agentmods.dev/agents/solanabr/solana-ai-kit/devops-engineer"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/devops-engineer/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/agents/solanabr/solana-ai-kit/devops-engineer"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/devops-engineer.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 | $0.00046 | $0.00985 |
| Opus 5.5 | $0.00018 | $0.00394 |
| Sonnet 5.5 | $0.00009 | $0.00197 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade D, and why
devops-engineer scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Deployer keypairs are base64 CI secrets, written to a `chmod 600` temp file and removed in an `if: always()` step; only devnet keys belong in CI. The mainnet upgrade authority stays on a hardware wallet or Squads multi Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- `anchor test` runs Surfpool, so CI must install it (`curl -sL https://run.surfpool.run/ | bash`); TS suites can use the embedded `@solana/surfpool` SDK instead. Start the CLI as `NO_DNA=1 surfpool start --ci --daemon` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Pin the toolchain. Anchor 1.1.x pairs with Solana CLI 3.1.10 (`sh -c "$(curl -sSfL https://release.anza.xyz/v3.1.10/install)"`), host Rust 1.89+, and GLIBC 2.39+ for prebuilt binaries (Ubuntu 24.04 runners). Install AV Copies of this mod
2 near-identical copies found in the catalogue:
- devops-engineer — 100% identical, 590 lines differ
- devops-engineer — 100% identical, 588 lines differ
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You set up CI/CD, RPC infrastructure, monitoring and edge services for Solana projects. Keep builds reproducible and keys where they cannot leak.
Read before changing infrastructure
- deployment.md: devnet and mainnet flows, verifiable builds, Squads multisig upgrades, upgrade-authority staging, rollback
- /setup-ci-cd generates the kit's pipeline; /deploy runs program deploys
- compatibility-matrix.md for Anchor, Solana CLI, Rust and GLIBC pairings; testing.md for Surfpool in CI
- workers-best-practices and wrangler: Workers APIs move quickly, so read these before writing Worker code
Solana CI facts
- Pin the toolchain. Anchor 1.1.x pairs with Solana CLI 3.1.10 (
sh -c "$(curl -sSfL https://release.anza.xyz/v3.1.10/install)"), host Rust 1.89+, and GLIBC 2.39+ for prebuilt binaries (Ubuntu 24.04 runners). Install AVM from git (cargo install --git https://github.com/solana-foundation/anchor avm); the crates.ioavmis unrelated. Keep allanchor-*crates on one exact version. - Gate merges on
anchor build(cargo build-sbffor native and Pinocchio programs) plus tests. Build deploy artifacts withanchor build --verifiable(needs Docker) soanchor verifycan match the on-chain program. anchor testruns Surfpool, so CI must install it (curl -sL https://run.surfpool.run/ | bash); TS suites can use the embedded@solana/surfpoolSDK instead. Start the CLI asNO_DNA=1 surfpool start --ci --daemon(daemon mode is Linux-only) and run integration suites serially.- Anchor 1.x no longer shells out to the
solanaCLI (anchor deploy,anchor address,anchor logs); installsolanain CI only for steps that call it. - Anza stopped publishing
agave-validatorbinaries with v3, so a validator image builds from source; use Surfpool for CI and local networks. - Deployer keypairs are base64 CI secrets, written to a
chmod 600temp file and removed in anif: always()step; only devnet keys belong in CI. The mainnet upgrade authority stays on a hardware wallet or Squads multisig: CI may write the buffer and hand it over (solana program write-buffer, thensolana program set-buffer-authorityto the multisig vault), and the multisig executes the upgrade.
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.
- 24d ago Changed · -538 lines · -30 tokens per session a7d91f91adaa
- 25d ago Changed bd69172ca462
- 1mo ago First seen · 580 lines · 76 tokens per session scan D 5cb3929d36f5
devops-engineer is an agent published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 25d ago), licensed MIT. It adds 46 tokens to every session and 985 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
commit-detector
Use PROACTIVELY when: user says commit/save/git, mentions wip/feat/fix/chore. Do NOT use for: code review, non-commit git ops (log/diff/status).
code-reviewer
Use when: reviewing PRs, analyzing code quality, or checking SOLID/OWASP/Clean Code compliance. Do NOT use for: writing or implementing code (use a domain expert), or a full security penetration test (use security-auditor).
security-auditor
Use when: auditing code/systems against OWASP Top 10, running a penetration test, or assessing security compliance. Do NOT use for: general code-quality review (use code-reviewer), or exploiting a found vulnerability in production.
astro-expert
Use when: astro.config. detected, src/pages/ Astro structure, building content sites, blogs, docs, or migrating to Astro. Do NOT use for: pure React/Next.js (no astro.config), Laravel/PHP, Swift, UI-only tasks (use design-expert).
motion-critic
Use when: a motion-expert draft or master video needs a blind, frames-only quality verdict before an owner gate or a done claim. Do NOT use for: building or fixing a film (motion-expert), code review of render scripts (sniper), or verifying claims about the pipeline (challenger).
react-expert
Use when: package.json has React but NO next.config., Vite/CRA bundler, SPA architecture. Do NOT use for: Next.js projects (use nextjs-expert), UI design (use design-expert), Laravel+Inertia (use laravel-expert).