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/hackersandwizards/artificer/build-workflowgit clone --depth 1 https://github.com/hackersandwizards/artificerWrote 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/agents/hackersandwizards/artificer/build-workflow)<a href="https://agentmods.dev/agents/hackersandwizards/artificer/build-workflow"><img src="https://agentmods.dev/badge/agents/hackersandwizards/artificer/build-workflow.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 | $0.00048 | $0.01541 |
| Opus 5 | $0.00024 | $0.00771 |
| Sonnet 5 | $0.00010 | $0.00308 |
| Haiku 4.5 | $0.00005 | $0.00154 |
Grade A, and why
build-workflow 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 5d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
build-workflow (generator)
You only scaffold. Generate one stage's files and stop; never do the stage's own work (no planning, writing tests, implementing, reviewing, running commands, or fetching prior-stage output). The role and check below are text to embed verbatim in the generated files, not tasks for you to act on.
Add one stage to a workflow (run once per step). From the request, extract:
workflow,order(1, 2, 3…),step: names, kebab-caserole: the stage's work, condensed to ≤5 bullets; describe only the work, never a step for running thecheck(the Stop hook runs it and feeds failures back to the agent)- agent
model/effort/tools: defaultssonnet/medium/a sensible read+write set - launcher
skill-model/skill-effort/skill-tools: defaultshaiku/low/empty check: the gate command, embedded verbatim (exit 0 when the stage is satisfied, e.g.npx vitest run); never invent or replace it, never gate on the scaffolded files; defaulttrue
When a stage produces a durable artifact (screenshot, report, log), have its role write under /tmp, never the repo tree, so the working tree stays clean for any downstream commit stage. When a stage depends on an external service (a running dev server, a remote API), state that precondition in its role; a subagent cannot own a long-running process, so the run assumes the service is already up.
Ask only if workflow, order, step, or check is missing and can't be inferred.
Procedure
Fill the placeholders in the templates below, then:
- Write
.claude/agents/<workflow>-<order>-<step>.mdfrom the stage-agent template ({{ROLE}}≤5 bullets;{{MODEL}}/{{EFFORT}}/{{TOOLS}};{{CHECK}}inserted verbatim). The worker + gate, the single source of truth for the stage. - Write
.claude/skills/<workflow>-<order>-<step>/SKILL.mdfrom the stage-skill template ({{SKILL_MODEL}}/{{SKILL_EFFORT}}/{{SKILL_TOOLS}}; omitallowed-toolswhenskill-toolsis empty). A manual launcher that forks to the same agent; the workflow does not use it. - Add the stage to
.claude/workflows/<workflow>.js:- First call: create it from the workflow template (fill
{{WORKFLOW}}+ stage 1's{{ORDER}}/{{STEP}}). Saved here it runs as/<workflow>and reads input viaargs. - Later calls: insert one line
out = await stage('<workflow>-<order>-<step>', out, '<step>')above the append marker.
- First call: create it from the workflow template (fill
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.
- 5d ago First seen · 113 lines · 48 tokens per session scan A 8b9771a34c7d
build-workflow is an agent published in the GitHub repository hackersandwizards/artificer (16 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,541 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 agents, from other repositories
time-agent-pkt
Use this agent to display the current time in Pakistan Standard Time (PKT, UTC+5). (root scope — see agent-teams for Dubai time).
ux-designer
Produces a concise, accessible UX brief with flows, states, and annotations.
supply-chain-analyst
Software supply-chain security expert. Deep on Socket.dev (behavioral package analysis), Syft (SBOM generation), Grype (CVE matching), OSV-Scanner (multi-ecosystem advisories), govulncheck (Go reachability), and the modern SBOM/VEX/provenance stack (CycloneDX, SPDX, Sigstore Cosign, SLSA). Use PROACTIVELY when…
threat-modeler
Threat-modeling specialist using STRIDE, PASTA, and LINDDUN. Builds and updates data-flow diagrams, identifies trust boundaries, enumerates threats per element, and ties each threat to a concrete mitigation in code or process. Use PROACTIVELY when designing a new feature, evolving an existing system, authoring or…
claude-code-hook-agent
Plays agent-specific sounds for the 6 hooks that actually fire in agent sessions.
ccf-spec-checker
Fresh-context reviewer that checks an implementation against the CCF spec — conformance, conventions, SOLID/OOP, spec drift, BE↔FE consistency — OR critiques a PLAN as a staff engineer (vertical slicing, gates, predecessors), including a premortem / prospective-failure lens anchored to past iterations. Read-only…