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 skills/dioptx/weft/wf-startnpx skills add dioptx/weft --skill wf-startgit clone --depth 1 https://github.com/dioptx/weftWhat 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 | $0.00024 | $0.00477 |
| Opus 5 | $0.00012 | $0.00238 |
| Sonnet 5 | $0.00005 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
wf-start 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.
What it actually says
Start Weft Workflow
Initialize a new deterministic workflow.
Arguments
$ARGUMENTS
Instructions
If no arguments — guided template picker:
-
List available templates with full details:
python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" start -
For each template, show a preview of its steps:
python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" preview <name> -
Present the user with a numbered list like:
1. generic (3 steps) — plan, implement, verify 2. feature-workflow (12 steps) — full-cycle feature development with guards 3. Custom — describe your task and I'll build a workflow -
Wait for the user to pick a number, name, or describe their task.
- If they pick a template: show the full preview and ask to confirm before starting.
- If they describe a task: suggest appropriate steps, confirm, then start as ad-hoc.
If a template name is given:
-
Preview it first:
python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" preview <template-name> -
Start it:
python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" start <template-name>
If comma-separated step names are given (ad-hoc):
python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" start "step1,step2,step3"
After starting:
Display the workflow checklist and remind the user:
/wf-step completeto advance steps/wf-statusto check progress/wf-analyzeto review timing and recurring friction across runs- The Stop hook will prevent finishing with incomplete steps
- If the current step has guards, explain what commands are blocked and 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.
- 3d ago First seen · 66 lines · 24 tokens per session scan A a451a97a9488
wf-start is a skill published in the GitHub repository dioptx/weft (22 stars, last pushed 18d ago), licensed MIT. It adds 24 tokens to every session and 477 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 2026-08-30.
Other skills, from other repositories
superpowers-graph
Runs the Superpowers software-development methodology as a guarded state machine — brainstorm, spec, plan, isolated workspace, the per-task implement/review/fix loop, the whole-branch review, and the integration menu — with typed node contracts, total exit guards, bounded retry loops, and a ledger recording every step…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
n8n:nathan
Deploy a temporary n8n test instance (or generate a local docker run command) via the internal "Nathan" bot, from the repo instead of Slack. Use after opening a PR to offer the user a live test instance, or whenever someone asks to spin up / deploy a test instance for a branch.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).