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 instructions/sjarmak/agent-workflows/agents-mdgit clone --depth 1 https://github.com/sjarmak/agent-workflowsWhat 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 | $0.01005 | $0.01005 |
| Opus 5 | $0.00502 | $0.00502 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade C, and why
agent-workflows AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf directory # NOT: rm -r directory How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This project uses bd (beads) for issue tracking. Run bd onboard to get started.
Quick Reference
bd ready # Find available work
bd show <id> # View issue details
bd update <id> --claim # Claim work atomically
bd close <id> # Complete work
bd dolt push # Push beads data to remote
ZFC Enforcement
This project is AI-orchestration code. Apply Zero Framework Cognition at two levels:
- L2 (tooling): workflow skills must not use heuristics for semantic judgment
- L3 (product): patterns embedded in workflow outputs shape how users approach their own AI-mediated work
Review checklist for agents
When reviewing or writing workflow skills, flag:
- Synthesis phases that use scoring formulas instead of model judgment
- Hardcoded classification of agent outputs (keyword matching for "done"/"failed")
- Winner selection via metric formula instead of model comparison
- Any code that makes a quality or relevance judgment without a model call
Ask: "Is this a mechanical/structural operation, or is it making a judgment a model should make?"
Compliant patterns to preserve
- Spawn independent agents → model synthesizes (core architecture)
- Convergence/divergence as signal, not as scored metric
- Agents provide semantic inputs (severity, likelihood), math is mechanical
Justified exceptions
brainstorm/scripts/similarity.py— calibrated duplicate detection with--forceescape hatch- Risk Score multiplication — deterministic math on agent-provided semantic inputs
- Task readiness via
bd ready— pure status-field logic
Non-Interactive Shell Commands
ALWAYS use non-interactive flags with file operations to avoid hanging on confirmation prompts.
Shell commands like cp, mv, and rm may be aliased to include -i (interactive) mode on some systems, causing the agent to hang indefinitely waiting for y/n input.
Use these forms instead:
# Force overwrite without prompting
cp -f source dest # NOT: cp source dest
mv -f source dest # NOT: mv source dest
rm -f file # NOT: rm file
# For recursive operations
rm -rf directory # NOT: rm -r directory
cp -rf source dest # NOT: cp -r source dest
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 · 119 lines · 1,005 tokens per session scan C c70cf168a674
agent-workflows AGENTS.md is an instructions file published in the GitHub repository sjarmak/agent-workflows (9 stars, last pushed 1mo ago), licensed MIT. It adds 1,005 tokens to every session, about $0.0050 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
ai-platform-engineering AGENTS.md
Instructions for caipe-io/ai-platform-engineering, covering agent instructions, project structure, find the canonical implementation, documentation and docs & spec rules.
playbooks CLAUDE.md
Instructions for playbooks-ai/playbooks, covering claude.md, project overview, core architecture, framework components and key architectural insights.
openhermit AGENTS.md
Instructions for HCF-STUDIOS/openhermit, covering openhermit workspace rules, general, code changes, testing and commits.
ai-platform-engineering CLAUDE.md
Instructions for caipe-io/ai-platform-engineering, a project described as: CAIPE is an open-source AI platform for building, deploying, governing, and operating AI agents and agentic workflows for platform engineering and beyond.
bureau CLAUDE.md
Claude Code instructions for Novadiem-Studio/bureau, covering novadiem studio ai framework — the bureau, canonical copy and drift, what this does, three-role model (notary / delegate / principal) and default entrypoint.
bureau AGENTS.md
AGENTS.md instructions for Novadiem-Studio/bureau, covering novadiem studio ai framework — the bureau, codex workspace instructions, canonical copy and drift, what this does and default entrypoint.