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/akka/ai-marketplaceWrote 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/commands/akka/ai-marketplace/build)<a href="https://agentmods.dev/commands/akka/ai-marketplace/build"><img src="https://agentmods.dev/badge/commands/akka/ai-marketplace/build/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/commands/akka/ai-marketplace/build"><img src="https://agentmods.dev/badge/commands/akka/ai-marketplace/build.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 | $0.00023 | $0.01013 |
| Opus 5 | $0.00012 | $0.00507 |
| Sonnet 5 | $0.00005 | $0.00203 |
| Haiku 4.5 | $0.00002 | $0.00101 |
Grade A, and why
build 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 9d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Purpose
This command is the local development loop. It compiles, tests, and runs
the service locally so you can iterate quickly. No Docker images are built,
no containers are pushed, no platform deployments happen. When the service
works locally and you're ready to ship, hand off to /akka-specify:deploy.
Outline
-
Compile: Use the
akka_maven_compileMCP tool to compile the project. If compilation fails, the tool returns extracted[ERROR]lines — read them, report to the user, and fix the code before proceeding. -
Test: Use the
akka_maven_testMCP tool to run all tests. If tests fail:- The tool returns test failure details and
[ERROR]lines - Report which tests failed and why
- Suggest fixes based on the failure messages
- Stop and hand off to
/akka-specify:implementfor fixes
- The tool returns test failure details and
-
Start local environment: Use the
akka_local_startMCP tool to start the local development environment in the background. Tell the user that the local runtime is starting — it provides gRPC proxying, service discovery, and trace collection onlocalhost:9889. This is idempotent — if already running, tell the user it is already active and report its status. -
Run the service: Use
akka_local_run_serviceto start the service locally. This tool compiles first (catching errors immediately), then runsmvn exec:javain the background. Tell the user the service is launching against the local runtime.- Pass the
environmentparameter to set additional environment variables (e.g.{"LOG_LEVEL": "DEBUG", "DB_HOST": "localhost"}). These are merged with the current environment — useful for config overrides, debug flags, or connecting to external services during local development.
- Pass the
-
Verify: Use
akka_local_statusto confirm the service registered. Useakka_local_logswithsource: "service"to check for runtime errors. Test endpoints through the local proxy (localhost:9889). Tell the user the service endpoint URL and whether it started successfully.
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.
- 9d ago First seen · 93 lines · 23 tokens per session scan A d47083f5ee5c
build is a command published in the GitHub repository akka/ai-marketplace (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 1,013 once invoked, about $0.0001 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 commands, from other repositories
kiro-steering-custom
Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.
autospec.plan
Generate YAML implementation plan from feature specification.
kiro-validate-design
Command "kiro-validate-design" from gotalab/cc-sdd, covering technical design validation, core task, execution steps, important constraints and tool guidance.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.
devs-team
Parallel multi-lens critique of a solution design (the active spec if present, else the decision brief). Dispatches 5 engineering lenses, merges findings, reports a verdict. Report-only, never blocks.
code-locate
Given a behavior description, locate candidate code paths and line ranges in the active codebase that probably implement it. Output up to 10 candidates with HIGH/MEDIUM/LOW confidence, one-line rationale per candidate, and an explicit search trail; propose a SOURCEOFTRUTH.md update so the next workflow step (typically…