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 engindemirog/ai-native-engineering-workspace --skill new-featuregit clone --depth 1 https://github.com/engindemirog/ai-native-engineering-workspaceWrote 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/engindemirog/ai-native-engineering-workspace/new-feature)<a href="https://agentmods.dev/skills/engindemirog/ai-native-engineering-workspace/new-feature"><img src="https://agentmods.dev/badge/skills/engindemirog/ai-native-engineering-workspace/new-feature/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/engindemirog/ai-native-engineering-workspace/new-feature"><img src="https://agentmods.dev/badge/skills/engindemirog/ai-native-engineering-workspace/new-feature.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 | $0.00036 | $0.00327 |
| Opus 5.5 | $0.00014 | $0.00131 |
| Sonnet 5.5 | $0.00007 | $0.00065 |
| Haiku 4.5 | $0.00004 | $0.00033 |
Grade A, and why
new-feature 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 9d 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
Read AGENTS.md and workflows/segments.md ("The chainer"). Determine the Mode line first.
Rule: Segments always stop; $new-feature flows only as far as the mode allows.
- strict — refuse before any stage (in the chat language, command names verbatim): "Mode is strict: stages are role-owned. Analyst starts with $analyze; subsequent roles run $plan, $build, $review, $verify in their own sessions."
- unset — stop; bootstrap has not run (run $bootstrap).
- lite — chain $analyze → $plan → $build → $review → $verify for the feature described after the skill name, entry checks included. Stop at the four gates (spec approval, plan approval, triage, ship), one decision per gate message (workflows/segments.md, Contract, Gate). If a matching spec exists in specs/active/, resume from its next gate — never a twin spec. REVIEW cannot be independent inside this session: at that gate, tell the human to open a fresh Codex session and run $review there, then paste the findings back here for triage. When the one-pass review conditions hold (workflows/segments.md, "The chainer"), say so: that session may run $verify too on a clean verdict.
What ships with it
1 file 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.
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.
- 9d ago Changed 22f3ab07b0b9
- 11d ago Changed · +2 lines 0fbc679c85d2
- 20d ago First seen · 17 lines · 36 tokens per session scan A 7633daec2777
new-feature is a skill published in the GitHub repository engindemirog/ai-native-engineering-workspace (114 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 327 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 2026-10-20.
new-feature compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| new-featureengindemirog/ai-native-engineering-workspace | Skill | 114 | 4d ago | MIT | A | 36 | Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | 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 | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |