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.
git clone --depth 1 https://github.com/kok-o/contextos-agentsWrote 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/rules/kok-o/contextos-agents/engineering-workflow)<a href="https://agentmods.dev/rules/kok-o/contextos-agents/engineering-workflow"><img src="https://agentmods.dev/badge/rules/kok-o/contextos-agents/engineering-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/rules/kok-o/contextos-agents/engineering-workflow"><img src="https://agentmods.dev/badge/rules/kok-o/contextos-agents/engineering-workflow.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00027 | $0.00340 |
| Opus 5.5 | $0.00011 | $0.00136 |
| Sonnet 5.5 | $0.00005 | $0.00068 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
engineering-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 today.
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
Skill: engineering-workflow
Resolve supporting resource paths relative to .agents/core/skills/engineering-workflow. Read examples and references only when needed.
engineering-workflow
Overview
Define the outcome, plan substantial changes, implement, verify, review, and report. Existing user authorization carries forward.
When to Use
Implementation, debugging, reviews, and release preparation. Routine maintenance and diagnostics use targeted checks.
Rules & Patterns
Establish acceptance criteria for substantial or ambiguous work. Ask only for missing decisions affecting scope, safety, or external actions. An implementation request authorizes ordinary reversible work. Inspect affected code and callers, preserve unrelated changes, and verify behavior before reporting completion. Roles are optional.
Read references/workflow.md for procedures when needed.
Code Examples
A README typo needs a small edit and formatting check. An authorization fix needs an allowed-user case and a denied-user regression.
Validation Checklist
- The requested outcome and applicable failure cases are checked.
- Evidence names commands, results, scope, and limitations.
- Unrelated changes and existing authorization are preserved.
Common Mistakes
Repeated approval after authorization; full ceremonies for routine edits; treating headings, role labels, or schema checks as behavioral proof.
Integration Notes
Use security for sensitive boundaries, ponytail-mindset for implementation complexity, and context-os for compiler/configuration work. gstack-roles is a compatibility alias.
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.
- today First seen · 44 lines · 27 tokens per session scan A e9a82e6d7c59
engineering-workflow is a cursor rule published in the GitHub repository kok-o/contextos-agents (10 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 340 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-25.
Other cursor rules, from other repositories
shell-scripts
Shell Scripts.
read-xlsx
Reading, writing, diffing, and repairing spreadsheets (.xlsx) for AI agents via the xfa MCP server.
shell-first-search
Search-tool fallback when Grep/Glob hang (>30 s on Windows hosts) or are unavailable — kill the PID, retry narrower, fall back to shell grep/ls/find.
scheduler-protocol
A set of instructions for creating and managing scheduled jobs that start agent sessions at a specified time or interval.
veta
Install, sync, and query the local Veta X bookmark library.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.