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-run-stepnpx skills add dioptx/weft --skill wf-run-stepgit clone --depth 1 https://github.com/dioptx/weftWrote 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/dioptx/weft/wf-run-step)<a href="https://agentmods.dev/skills/dioptx/weft/wf-run-step"><img src="https://agentmods.dev/badge/skills/dioptx/weft/wf-run-step.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00730 |
| Opus 5 | $0.00023 | $0.00365 |
| Sonnet 5 | $0.00009 | $0.00146 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
wf-run-step scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a Weft Step as a Workflow
For steps whose template declares an executor (a Claude Code Workflow script), this runs the
workflow, captures its structured verdict, and pipes the result to weft run-result — which records
the Workflow runId on the step (for crash-resume) and auto-transitions: complete if the verdict is
non-blocking, fail (per on_fail) if blocking.
Steps with no executor are not for this skill — drive them with /wf-step as normal. The executor
is for mechanical steps (review fan-out, multi-target verification, regression sweeps); judgment gates
stay human-driven.
1. Read the current step's executor
python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" status --json
Find the current step (the one with status: running). Read its executor field:
executor.type— currently only"workflow"is supported.executor.script— script name, resolved to~/.claude/weft/workflows/<script>.js(or the project-local.claude/weft/workflows/<script>.jsif present).executor.args— JSON args passed to the workflow.
If executor is null: stop. Tell the user this step has no executor and should be advanced with
/wf-step. Do not invent one.
2. Invoke the Workflow
If --resume was passed AND the step already has a non-null workflow_run_id, re-invoke with
resumeFromRunId so completed sub-agents return cached (this is the crash-resume path):
Workflow({ scriptPath: "<resolved path>", args: <executor.args>, resumeFromRunId: "<workflow_run_id>" })
Otherwise invoke fresh:
Workflow({ scriptPath: "<resolved path>", args: <executor.args> })
The executor script must return an object that includes at least blocking (boolean) and a
human-readable summary. Capture the Run ID from the tool result and the returned object.
3. Record the verdict and auto-transition
Build the payload and pipe it to run-result (it transitions the step — complete if not blocking,
fail if blocking):
echo '{"run_id":"<RUN_ID>","blocking":<true|false>,"reason":"<one-line>","verdict":<the returned object>}' \
| python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" run-result
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.
- 4d ago First seen · 70 lines · 46 tokens per session scan A aa1b8925dc41
wf-run-step is a skill published in the GitHub repository dioptx/weft (23 stars, last pushed 19d ago), licensed MIT. It adds 46 tokens to every session and 730 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
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。.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
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.