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/implementgit clone --depth 1 https://github.com/Oriolshhh/runware-image-mcpWhat 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 | $0.00033 | $0.00974 |
| Opus 5 | $0.00016 | $0.00487 |
| Sonnet 5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
implement 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 2d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/implement — Implement an approved spec
Purpose
Deliver the approved spec with tests and green gates.
Invocation
/implement <spec name>
Accepted input
An approved spec under .agent/specs/.
Prerequisites
An approved spec. If none exists, run /spec first.
Procedure
- Confirm an approved spec exists.
If it declares
work_type: frontend-redesign, hand it to/implement-spec-frontend; the generic path does not provide the required baseline comparison and independent visual-craft review. If it declareswork_type: frontend-image-polish, require one explicitly approved tier, applyimage-art-direction, generate only the listed assets through an available user-approved image tool/provider, preserve the spec's exact style lock and per-slot dimensions, then route integration tofrontend-implementerand rendered comparison tovisual-qa-tester. - Classify the approved tasks before implementation. For user-facing rendered
UI work, route those tasks to
frontend-implementerand applyfrontend-guidelines,design-system-integration,ui-state-design,responsive-ui-engineering, andaccessible-ui-engineeringalongsideminimal-diff,test-design, andcode-quality-guidelines. Keep non-UI tasks withimplementer. - If the frontend spec lacks an approved visual direction or makes material
brand, navigation, interaction, or shared design-system decisions, stop and
hand that scope to
/frontend-design; do not invent the direction while coding. - Apply engineering guidelines by surface before editing:
- always apply
code-quality-guidelines; - apply
architecture-guidelinesfor new abstractions, shared modules, APIs, data flow, refactors, migrations, or cross-boundary changes; - apply
backend-guidelinesfor server-side, CLI, persistence, validation, integrations, auth, jobs, or operational work; - apply
frontend-guidelinesfor rendered UI, components, routes, browser behavior, frontend state, or design-system work.
- always apply
- Implement the spec's dependency-ordered tasks with the smallest reasonable
diff. Use
motion-designonly when motion is explicitly in scope or changed. - Add or update tests so the spec's test plan is satisfied. For rendered UI
changes, hand the result to
visual-qa-testerand applybrowser-visual-validation; verify relevant states, viewports, keyboard/focus, zoom/reflow, reduced motion, and runtime console/network behavior. - Run the gates (install, lint, typecheck, test, build) and make them pass.
- Summarize what changed, requirements satisfied, routing used, guidelines applied, browser evidence when applicable, and gates run.
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.
- 2d ago First seen · 92 lines · 33 tokens per session scan A cb45b8c37144
implement is a command published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 974 once invoked, about $0.0002 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.