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 agentmods add commands/oriolshhh/runware-image-mcp/invokegit clone --depth 1 https://github.com/Oriolshhh/runware-image-mcpWrote 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/oriolshhh/runware-image-mcp/invoke)<a href="https://agentmods.dev/commands/oriolshhh/runware-image-mcp/invoke"><img src="https://agentmods.dev/badge/commands/oriolshhh/runware-image-mcp/invoke.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00888 |
| Opus 5 | $0.00012 | $0.00444 |
| Sonnet 5 | $0.00005 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
invoke 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 3d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/invoke — Route a request to the right specialist workflow
Purpose
Let the user ask naturally for work such as "review this spec", "fix this bug", "implement this small task", or "improve this UI" without needing to remember the exact HarnessKit command.
Invocation
/invoke <what you want done>
Examples:
/invoke review .agent/specs/billing-limits.md before I approve it
/invoke fix the failing lockfile ownership test
/invoke add a small --json flag to context status
/invoke improve the pricing page hero and verify it in browser
Accepted input
A natural-language request plus any relevant files, specs, diffs, failing commands, screenshots, tickets, or constraints.
Prerequisites
A HarnessKit workspace. For implementation of non-trivial changes, either an approved spec or explicit user permission to perform a small no-spec change.
Procedure
- Invoke
task-router. - Apply
requirements-triage,specialist-routing,model-routing, andcontext-discoveryas needed. - Classify the request into one of these route families:
- planning:
/spec,/spec-detailed,/council,solution-council; - implementation:
/implement,spec-to-implementation,/frontend-design,frontend-implementation,/implement-spec-frontend; - diagnosis:
/debug,debug-loop; - review:
/review,/ui-review,/sum-spec, focused reviewer agents; - repair:
/fix,review-fix,ui-review; - context or configuration:
/build-context,/compress-context,/agent,/pack. Route a major redesign of an existing frontend surface to/spec-frontend; keep/improve-ui-uxfor scoped reversible polish and/frontend-designfor net-new surfaces. Route requests to add a coherent family of images or illustrations to an existing page to/polish-with-images.
- planning:
- Choose the smallest safe route. Use direct specialist role passes only for bounded work that does not need a full command or loop. Use a loop only when iterative behavior is required or the user requested an end-to-end workflow.
- Announce the route in one compact sentence: "Routing to X because Y."
- If the request is blocked by missing decision-changing information, ask one grouped question batch and stop. Do not drip-feed questions.
- Otherwise, read the selected route's canonical
.agent/instruction file in full and execute it.
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.
- 3d ago First seen · 97 lines · 23 tokens per session scan A 2955349d916c
invoke is a command published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 888 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.