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-stepnpx skills add dioptx/weft --skill wf-stepgit 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 | $0.00020 | $0.00691 |
| Opus 5 | $0.00010 | $0.00345 |
| Sonnet 5 | $0.00004 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
wf-step 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advance Weft Workflow Step
Transition the current step to a new status.
Arguments
$ARGUMENTS
Parsing
Parse the arguments flexibly. The user may say:
/wf-step complete "planning done"— standard form/wf-step doneor/wf-stepwith no args — treat ascomplete/wf-step skip not needed— skip with reason/wf-step failed, try again— treat asretryif step is failed, orfailif running/wf-step complete 3or/wf-step complete next 3— bulk complete N steps
Map natural language to actions:
| User says | Action |
|---|---|
| done, finished, complete, next | complete |
| skip, not needed, pass | skip |
| failed, broken, error | fail |
| retry, again, redo | retry |
| again, loop, iterate, continue loop, not done yet, issues remain | loop-continue |
| done looping, exit loop, loop done, clean, all clear | loop-done |
Loop disambiguation: If the current step has a loop_back_to field, prefer loop actions over regular ones. "again" on a loop step means loop-continue, not retry. "done" on a loop step means loop-done, not complete. If the user explicitly says "complete" or "skip", use those literally even on loop steps.
Single step transition
python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" step <action> <reason>
Bulk transitions
If the user specifies a count (e.g., "complete 3"), loop:
for i in 1 2 3; do
python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" step complete "bulk advance"
done
Stop looping if any step fails or the workflow completes.
After transition
- Display the updated workflow checklist.
- If the workflow just completed, congratulate and summarize what was accomplished.
- If a step failed with
blockpolicy, explain options:/wf-step retryor/wf-abort. - If the next step has guards, explain what commands are blocked.
- If the next step has a description in the template, mention what it expects.
After loop-continue
- Show "Loop iteration N/M" with the current count and max.
- List which steps were reset back to pending.
- If the exit condition is defined, remind the user what needs to be true to exit.
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 · 73 lines · 20 tokens per session scan A efbe7e260d00
wf-step is a skill published in the GitHub repository dioptx/weft (22 stars, last pushed 18d ago), licensed MIT. It adds 20 tokens to every session and 691 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).