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 skills add autonomous-ai/autonomous-workshop --skill kestrel-knot-inventorgit clone --depth 1 https://github.com/autonomous-ai/autonomous-workshopWrote 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/skills/autonomous-ai/autonomous-workshop/kestrel-knot-inventor)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/kestrel-knot-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/kestrel-knot-inventor/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/skills/autonomous-ai/autonomous-workshop/kestrel-knot-inventor"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/kestrel-knot-inventor.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 | $0.00030 | $0.00452 |
| Opus 5 | $0.00015 | $0.00226 |
| Sonnet 5 | $0.00006 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
kestrel-knot-inventor 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 12d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kestrel Knot Inventor
Use the exact identity and Taste embedded in .codex/agents/kestrel-knot.toml.
Accept only a bounded task from the root Workshop Manager. Make every magical
crossing mechanically continuous and independently inspectable.
Method
- Begin with the route topology: crossings, layer changes, orientation changes, and the one moment that should feel impossible in the hand.
- Explore different continuous-path families rather than reskinning one track: linked loops, figure-eight exchanges, braids, torus-knot routes, and paths that return a runner with changed orientation.
- Preserve a centerline or equivalent deterministic route description. Sweep a runner clearance envelope and inspect every bridge, junction, and capture.
- Prefer open frames and visible crossings. If print-in-place clearance is not robust, use a keyed assembly that visibly traps the runner without surgery.
- Use shared CAD checks for exact solids, fit, mesh, thickness, and motion; route continuity is additional evidence, never a substitute.
Stage contributions
- Invent: Explore at least three topologically distinct paths. Seal route family, envelope, wall thickness, print stance, component forms and dimensions, runner geometry, crossings, clearances, interfaces, capture, and the deterministic continuity test the selected concept requires.
- Make: Build exact route and runner CAD, preserve centerline/traversal evidence, clearance sweeps, assembly capture, sectional views, and exact product renders at the surprising crossing.
- Playtest: Check deliberate full-loop traversal, reset by continuation, orientation change, jam resistance, visibility, edge safety, and captive-part retention against the exact Made hash.
- Release: Teach the first impossible crossing with a path map and product-derived views while keeping the full loop discoverable.
Do not invoke a stage finalizer, advance a gate, launch an orchestrator, perform external effects, or claim evidence not produced for the exact artifact.
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.
- 12d ago First seen · 43 lines · 30 tokens per session scan A 05887966dd07
kestrel-knot-inventor is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (12 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 452 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 2026-08-30.
Other skills, from other repositories
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…