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 softspark/ai-toolkit --skill workflowgit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/workflow)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/workflow"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/workflow/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/softspark/ai-toolkit/workflow"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 9 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00023 | $0.02955 |
| Opus 5 | $0.00012 | $0.01477 |
| Sonnet 5 | $0.00005 | $0.00591 |
| Haiku 4.5 | $0.00002 | $0.00296 |
Grade A, and why
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 yesterday.
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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/workflow - Autonomous Agent Workflow
$ARGUMENTS
Autonomous software delivery
For autonomous-development, or an explicit request to carry a brief, spec,
issue or existing PR through implementation, review, QA and required CI, invoke
/autonomous-dev with the original task. It owns the run, durable state and
completion gate; do not also start the generic workflow below or initialize a
second run. Preserve existing approvals and inherited model/permission settings.
Use /autonomous-dev resume <run-id> for an interrupted run and
/autonomous-dev status <run-id> for read-only progress.
Step 1 — Select workflow type
Is production DOWN? → incident-response
Performance degraded >50%? → performance-optimization
Bug spanning multiple layers? → debugging
Warning / trend? → proactive-troubleshooting
Planned infra change? → infrastructure-change
Planned app deploy? → application-deploy
New feature (full stack)? → feature-development
New feature (backend only)? → backend-feature
New feature (frontend only)? → frontend-feature
New API endpoint? → api-design
Schema / migration change? → database-evolution
Boost test coverage? → test-coverage
Security assessment? → security-audit
Exploring unfamiliar codebase? → codebase-onboarding
Technical research / spike? → spike
Autonomous task-to-PR delivery? → autonomous-development (autonomous-dev)
Step 2 — Define success criteria (MANDATORY)
Cannot proceed without:
Deliverables: [what outputs are expected]
Verification: [how to verify — tests, metrics, commands]
Definition of done: [quality bar]
Present to user and wait for approval.
Step 3 — Spawn agents via Agent tool
Launch agents in parallel where independent, sequentially where dependent. Use the Agent tool — never do the work inline.
Existing workflows
debugging
# Sequential diagnosis:
Agent(subagent_type="debugger", prompt="Diagnose issue, 5 Whys, propose solution options. READ-ONLY.")
Agent(subagent_type="explorer-agent", prompt="Trace call path across layers. READ-ONLY.")
# Parallel fix:
Agent(subagent_type="backend-specialist", prompt="Implement fix. Own files: src/")
Agent(subagent_type="test-engineer", prompt="Write regression test. Own files: tests/")
# Sequential:
Agent(subagent_type="documenter", prompt="Document in kb/troubleshooting/ if recurring.")
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.
- yesterday Changed · +11 lines fa9128f4d07f
- 6d ago First seen · 251 lines · 23 tokens per session scan A 90b4e76182dd
workflow is a skill published in the GitHub repository softspark/ai-toolkit (170 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 2,955 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 2026-09-03.
Other skills, from other repositories
it-commercial-proposal
Génération d'offres commerciales pour des projets IT — lots techniques, chiffrage jour-homme, hypothèses, SLA, TMA et annexes techniques. Se déclenche avec "offre commerciale IT", "proposition commerciale IT", "devis IT", "appel d'offres", "offre technique et financière", "chiffrage jour-homme", "SOW", "réponse à AO".…
data-governance-guide
Gouvernance des données incluant catalogues, lineage, qualité, ownership, politiques et metadata management. Se déclenche avec "data governance", "gouvernance données", "data catalog", "data lineage", "metadata", "data ownership".
developer-onboarding-builder
Création de processus d'onboarding pour nouveaux développeurs. Se déclenche avec "onboarding", "nouveau développeur", "intégration équipe", "setup poste", "getting started guide", "accueil développeur". Also triggers on "onboard a new developer", "developer setup guide", "first week checklist".
orchestrator
Providerneutrales Protokoll zum Zerlegen komplexer Aufgaben, zum Beauftragen unabhängiger Worker und zur evidenzbasierten Abnahme ihrer Ergebnisse.
workflow-extract
Baut aus einem Chatverlauf oder aus bestehenden Automatisierungs-Prompts (z. B. eines anderen Agenten-Systems) eine selbstlaufende, user-neutrale Workflow-Automatisierung: einen wiederkehrenden Prompt bzw. Automations-Skill für Cron/Schedule/Loop. Alias: automations-extractor. Nutze diesen Skill bei „mach daraus eine…
project-onboarding
Standard procedure for onboarding new software projects: Feature analysis, code quality review, onboarding checklist, and task creation.