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 polaralias/skills --skill engineering-workflowgit clone --depth 1 https://github.com/polaralias/skillsWrote 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/polaralias/skills/engineering-workflow)<a href="https://agentmods.dev/skills/polaralias/skills/engineering-workflow"><img src="https://agentmods.dev/badge/skills/polaralias/skills/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/skills/polaralias/skills/engineering-workflow"><img src="https://agentmods.dev/badge/skills/polaralias/skills/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 | $0.00084 | $0.01227 |
| Opus 5.5 | $0.00034 | $0.00491 |
| Sonnet 5.5 | $0.00017 | $0.00245 |
| Haiku 4.5 | $0.00008 | $0.00123 |
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 18d 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Workflow
Select the engineering method that fits the user's immediate need, read its reference, and perform the work. Use the entry point to select the current method and its required outcome. Read only the relevant references.
Select a method
| Need | Read |
|---|---|
| Explain code, behaviour, a diff, or what changed | Comprehension |
| Make an inherited, unclear, or undocumented repository legible | Dissection |
| Resolve terminology, contradictory claims, or consequential intent | Clarification |
| Turn a resolved outcome into contracts, scenarios, acceptance, and work packages | Design |
| Implement, fix, refactor, test, or review a bounded code change | Delivery |
| Establish, capture, review, align, or streamline canonical repository knowledge | Knowledge |
| Maintain durable tasks, workstreams, effort, and execution evidence | Task lifecycle |
| Reconcile material work before claiming completion | Alignment |
| Preserve unfinished work across a pause or session boundary | Handoff |
| Resume and verify continuation evidence | Pickup |
| Allocate parallel ownership, branches, worktrees, integration, or cleanup | Coordination |
| Assess release readiness, review publication safety, or publish accepted work to a tracker | Publication |
The reference map shows conditional transitions between methods. Initial repository bootstrap remains outside this workflow.
Work proportionately
For a bounded correction: inspect the named source and relevant tests, fix it, run focused validation, review documentation impact as described in delivery, and explain the causal result. Do not create tasks, knowledge bundles, persistent workflow state, handoffs, or a release review merely to finish a small change. Honour existing repository obligations and report material limitations.
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 461 B
- assets/icon.svg 1.7 KB
- license.txt 117 B
- references/alignment.md 4.5 KB
- references/clarification.md 3.3 KB
- references/comprehension.md 4.2 KB
- references/coordination.md 5.7 KB
- references/delivery.md 5.1 KB
- references/design.md 6.0 KB
- references/dissection.md 4.4 KB
- references/handoff.md 4.8 KB
- references/knowledge.md 12 KB
- references/pickup.md 3.9 KB
- references/publication.md 5.1 KB
- references/reference-map.md 2.5 KB
- references/task-lifecycle.md 7.3 KB
- RKE_SOURCE.json 429 B
- tests/prompts.md 10 KB
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.
- 18d ago Changed · +4 lines d37158a2a472
- 19d ago Changed · -126 lines · -34 tokens per session efb9f15618fa
- 1mo ago Changed · +12 lines 7d959f2ed488
- 1mo ago First seen · 165 lines · 118 tokens per session scan A b742611f3b15
engineering-workflow is a skill published in the GitHub repository polaralias/skills (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,227 once invoked, about $0.0003 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 2026-09-19.
engineering-workflow compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| engineering-workflowpolaralias/skills | Skill | 2 | 10d ago | Apache-2.0 | A | 84 | Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |