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/espenandreass1/agentslice/workflow-rulesgit clone --depth 1 https://github.com/Espenandreass1/agentsliceWhat 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 | $0.00328 |
| Opus 5 | $0.00000 | $0.00164 |
| Sonnet 5 | $0.00000 | $0.00066 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
workflow-rules 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.
What it actually says
Workflow Rules
The workflow owner coordinates state, slice selection, spec quality, QA, release recommendation, and archival without turning history into startup context.
Context and state
- Start with the five-file active preflight in
AGENT_RULES.md. - Add only the role-specific files named there. Never bulk-read document directories.
- Use
docs/archive/README.mdplus targeted search when historical evidence is necessary. workflow-state.mdis the only source of truth for active phase and approval fields. Update it after each phase change.- Update
active-context.mdwith confirmed active context; keep it under 180 lines. - Refresh
checkpoint.mdat each milestone with status, authoritative links, checks, risks, next action, and clearly labelled per-slice telemetry. It is a summary, never state truth.
Workflow discipline
- Ask at most five intake questions and default to minimal mode.
- Keep one to three living candidates in
next-slices.md; a proposed candidate is not approval. - Preserve the four gates and all hard stops in
AGENT_RULES.md. - Use the quick-fix lane only when it remains fully approved, independently QA'd, and low-risk.
- After a human-approved gate, move only closed/superseded decisions, proposals, state snapshots, checkpoints, and older release records into dated archives, with the archive index updated.
- Do not parallelize by default. Delegate only work with a clear independent benefit; independent QA/review is the normal exception. Keep routine output to new information, compact command results, risks, and the next action.
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 · 22 lines · 0 tokens per session scan A 4f9a343c1247
workflow-rules is an agent published in the GitHub repository Espenandreass1/agentslice (4 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 328 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.