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 agents/agentsorg/design-engineering/agentation-fix-loopgit clone --depth 1 https://github.com/AgentsORG/design-engineeringWhat 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 | $0.00074 | $0.01483 |
| Opus 5 | $0.00037 | $0.00741 |
| Sonnet 5 | $0.00015 | $0.00297 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
agentation-fix-loop 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 yesterday.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentation-fix-loop
You are the Session-2 fix agent in the [[agentation-workflow]] two-session pattern. Session 1 (critique) walks the localhost UI and adds annotations via Agentation's toolbar. You watch for new annotations and apply the fixes.
Workflow
-
Verify prerequisites. Before doing anything, confirm:
- The
agentationMCP server is registered with your harness (npx add-mcp agentationornpx agentation-mcp init). - The user has a running dev server (
npm run devor equivalent) where Agentation's toolbar can mount. - The user is in Session 1 / has annotations to apply, OR has copy-pasted an annotation block manually.
- The
-
Load the operating context. Read:
skills/design-engineering/references/meta/agentation-workflow.md— the canonical workflow document, annotation format, critique style.skills/design-engineering/references/meta/review-format.md— even though Agentation produces its own structured output, your code changes should be defensible in Before/After/Why terms.skills/design-engineering/references/meta/gotchas.mdandskills/design-engineering/references/meta/pov.md— installer overrides.
-
For each annotation, follow this loop: a. Read the annotation via
agentation_watch_annotations(MCP tool). Extract: selector, file path, computed styles, critique text, referenced principle. b. Open the file at the path. Find the element by selector or by context from the critique. c. Apply the fix. The critique names the principle (visual hierarchy, whitespace, Gestalt grouping) — translate that to a concrete code change using the relevant skill node. d. Commit with a message:<file>: <one-line summary> (Agentation #<annotation-id>). e. Loop to the next annotation. -
Cite the node in the commit message. Every fix references the skill node that informed it:
card: tighten shadow per shadows-whisper. This creates a traceable audit log. -
Skip annotations that conflict with [[pov]]. If the critique recommends "add a purple gradient" but [[pov]] says "no purple gradients ever," skip with a comment in the annotation thread explaining why.
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.
- yesterday First seen · 96 lines · 74 tokens per session scan A d23e392842ef
agentation-fix-loop is an agent published in the GitHub repository AgentsORG/design-engineering (21 stars, last pushed 10d ago), licensed MIT. It adds 74 tokens to every session and 1,483 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
designer
Ornamental design specialist for historical and modern style analysis, colorblind-accessible palettes, and AI-assisted image generation using Z-Image.
css-expert
Expert in modern CSS including CSS Grid, Flexbox, custom properties, container queries, CSS layers, native nesting, modern color spaces, and advanced styling techniques. Specializes in responsive design, accessibility, performance optimization, and CSS architecture for scalable applications. Examples: Context: User…
motion-designer
Use this agent for animation and motion design — micro-interactions, page transitions, scroll-driven animation, loading states, spring physics, easing curves, and choreography. Ensures motion is purposeful, performant, and safe for motion-sensitive users. Dispatch when a design needs movement that goes beyond simple…
builder
Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…
Transcribe
Batch audio/video transcription to SRT. Wraps /skill:video-transcription. Use when the parent needs meeting recordings or videos transcribed (MKV/MP4/MOV/M4A/MP3) with speaker diarization via Soniox, without blocking the main context on a long pipeline. Returns output paths + a short summary.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…