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/inspect)<a href="https://agentmods.dev/commands/akka/ai-marketplace/inspect"><img src="https://agentmods.dev/badge/commands/akka/ai-marketplace/inspect/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/inspect"><img src="https://agentmods.dev/badge/commands/akka/ai-marketplace/inspect.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 | $0.00029 | $0.02075 |
| Opus 5 | $0.00015 | $0.01038 |
| Sonnet 5 | $0.00006 | $0.00415 |
| Haiku 4.5 | $0.00003 | $0.00208 |
Grade A, and why
inspect 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Purpose
This command inspects a running service at runtime. It exercises API
endpoints, verifies internal state through backoffice tools, and validates the
UI through browser tools — all driven by the feature specification. No
compilation or unit tests happen here; use /akka:build for that.
Outline
-
Pre-flight checks:
- Call
akka_local_statusto verify the service is running. If not running, stop and tell the user: "No service is running locally. Run/akka:buildfirst to compile, test, and start the service." - Call
akka_sdd_list_specsto find the target feature. If the user specified a feature name in$ARGUMENTS, match it. Otherwise, if there is exactly one feature, use it. If multiple features exist, ask the user which to inspect. - If no spec exists, stop and tell the user: "No feature specification
found. Run
/akka:specifyfirst to create one, or provide a feature name." - Read the spec.md for the target feature. Extract:
- API endpoints (paths, methods, expected request/response shapes)
- Entities and their expected events/state
- Workflows and expected step sequences
- Views and expected query results
- Agents and expected behavior
- Acceptance criteria to verify
- Call
-
Discover components: Call
akka_backoffice_list_componentswithlocal=trueto list all components registered in the running service.- Compare against what the spec defines — flag any components that are missing from the running service or present but not in the spec
- Report the component inventory: entities, views, workflows, agents, endpoints
-
Exercise API endpoints: For each endpoint defined in the spec, use
akka_local_requestto send requests and verify responses:- Happy path: Send valid requests matching the spec's examples or acceptance criteria. Verify HTTP status codes and response payloads.
- Command operations: POST/PUT/DELETE commands that mutate state. Execute these in the order that makes sense (e.g. create before update).
- Query operations: GET requests to read state back. Verify the response matches what the commands should have produced.
- Error cases: If the spec defines error scenarios (invalid input, not-found, conflict), test those too. Verify appropriate error responses.
- Record all request/response pairs for the report.
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 · 153 lines · 29 tokens per session scan A 07d3cbb591a0
inspect is a command published in the GitHub repository akka/ai-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 2,075 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
speckit.companion.doctor
Report on a spec's run health — unfinished steps, unjournaled tasks, step bleed, drift you can judge, a step that closed having verified nothing, a step that closed without the file it promised, and why completion did not land (read-only, retroactive, never halts).
kiro-validate-gap
Command "kiro-validate-gap" from gotalab/cc-sdd, covering implementation gap validation, core task, execution steps, important constraints and tool guidance.
jira-issue-use-cypress
Like /jira-issue-use-browser, but pinned to the Cypress MCP — use when your project runs the Cypress MCP for browser automation. Example — /jira-issue-use-cypress "Composer > Save" saving toasts failure but the record persists.
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…
interactive-dev
Start a persistent interactive development session with natural language browser control, auto-error monitoring, and full dev tool access.
im-stuck
Break the task out of a loop, confusion state, or false-progress state, and determine the fastest safe path forward. Diagnoses whether the issue is technical, workflow-related, or scope-related, then routes to the right recovery command and editor mode (Ask by default; Debug if the stuckness is a concrete technical…