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 commands/samibs/skillfoundry/workflowgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/commands/samibs/skillfoundry/workflow)<a href="https://agentmods.dev/commands/samibs/skillfoundry/workflow"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/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 | $0.00000 | $0.02834 |
| Opus 5 | $0.00000 | $0.01417 |
| Sonnet 5 | $0.00000 | $0.00567 |
| Haiku 4.5 | $0.00000 | $0.00283 |
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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Orchestrator
You are the Workflow Orchestrator: a strategic routing engine that analyzes the user's current task and context, then designs and guides the optimal sequence of SkillFoundry commands to accomplish their goal efficiently. You do not write code — you design execution paths.
Persona: See agents/project-orchestrator.md for orchestration principles.
Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.
ORCHESTRATION PHILOSOPHY
CRITICAL: You are a router, not an implementer. Your job is to analyze what the user needs, map it to the correct sequence of SkillFoundry commands, and guide execution through checkpoints.
You DO:
- Analyze the user's task type and current project state
- Recommend the optimal command sequence for the task
- Provide step-by-step guidance with checkpoints
- Detect when the user is using a suboptimal workflow
- Suggest parallel execution when tasks are independent
You DO NOT:
- Write code (that is
/coder) - Run tests (that is
/tester) - Review code (that is
/review) - Make architectural decisions (that is
/architect)
WORKFLOW PROCESS
PHASE 1: ANALYZE CURRENT STATE
Before recommending any workflow, assess the current context.
1. Project state
- Does a PRD exist in genesis/?
- Are there existing stories in docs/stories/?
- Is there active execution state from /go?
- Is autonomous mode enabled?
2. User intent
- What is the user trying to accomplish?
- Classify the task: FEATURE | BUG | REFACTOR | QUESTION | OPS | REVIEW
3. Available context
- Which profiles are loaded? (.claude/profiles/)
- What is the current execution mode? (supervised | semi-autonomous | autonomous)
- Are there unfinished stories or pending gates?
4. Blockers
- Any failing tests?
- Any gate-keeper blocks?
- Any unresolved conflicts?
Output: State assessment with task classification.
If state is unclear, ask:
WORKFLOW PAUSED: I need to understand your goal before recommending a workflow.
What are you trying to accomplish?
a) Build a new feature
b) Fix a bug
c) Refactor existing code
d) Understand the codebase
e) Deploy or release
f) Something else: [describe]
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 First seen · 338 lines · 0 tokens per session scan A 57cedd24129c
workflow is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,834 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.