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 jpantsjoha/ai-native-developer-experience --skill wrap-it-upgit clone --depth 1 https://github.com/jpantsjoha/ai-native-developer-experienceWrote 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/jpantsjoha/ai-native-developer-experience/wrap-it-up)<a href="https://agentmods.dev/skills/jpantsjoha/ai-native-developer-experience/wrap-it-up"><img src="https://agentmods.dev/badge/skills/jpantsjoha/ai-native-developer-experience/wrap-it-up/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/jpantsjoha/ai-native-developer-experience/wrap-it-up"><img src="https://agentmods.dev/badge/skills/jpantsjoha/ai-native-developer-experience/wrap-it-up.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 | $0.00132 | $0.03466 |
| Opus 5.5 | $0.00053 | $0.01386 |
| Sonnet 5.5 | $0.00026 | $0.00693 |
| Haiku 4.5 | $0.00013 | $0.00347 |
Grade A, and why
wrap-it-up 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 10d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wrap it up
The iteration is ending. Take what is already in flight, drive every item to a definite
exit, leave main a clean baseline, and tell the operator whether it is worth a tag.
Why you were invoked — read this before planning anything
This skill is a session-economics instruction as much as a delivery one. The operator reaches for it when some combination of these is true, and they are the constraints you work under from here:
- The session is long and the context window is filling. Every token spent re-reading a file you already summarised is a token not spent landing work.
- They are not watching. No question you ask will be answered in time. Bank decisions, never block on them, and never end a turn with "shall I".
- They do not want to babysit an engineering session. The value you deliver now is a clean trunk and a truthful tracker, not a demonstration of effort.
Three behaviours follow, and they are not optional:
- Delegate execution; keep orchestration. Push implementation into subagents and worktrees so their file reads and failed attempts never enter this context. Read a subagent's report, never its transcript. Long-running commands go to the background and are polled, not watched.
- Delegate judgement to the council, not to more of your own thinking. Audit, adversarial planning and PR review go to an independent fresh-context reviewer under the Council contract, in the project's review order. One lane per question; a second lane only when the disagreement is worth paying for. You still re-derive the gate yourself — that never delegates.
- Spend the remaining budget on exits, not on polish. An item that is 90% done and needs another design round is a deferral with a record, not a reason to keep going. Closing the session honestly beats landing one more thing badly.
Focus is the point — the failure this skill exists to prevent
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.
- 10d ago First seen · 244 lines · 132 tokens per session scan A 21421b4b563a
wrap-it-up is a skill published in the GitHub repository jpantsjoha/ai-native-developer-experience (13 stars, last pushed 11d ago), licensed Apache-2.0. It adds 132 tokens to every session and 3,466 once invoked, about $0.0005 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 2026-11-10.
wrap-it-up compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wrap-it-upjpantsjoha/ai-native-developer-experience | Skill | 13 | 11d ago | Apache-2.0 | A | 132 | Claude Code |
| security-ownership-mapHKUDS/DeepCode | Skill | 17k | 3d ago | MIT | A | 99 | Codex |
| finishing-a-development-branchrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 44 | Claude Code, Codex |
| using-git-worktreesrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 36 | Claude Code, Codex |
| comet-archiverpamis/comet | Skill | 3.3k | yesterday | MIT | A | 35 | Claude Code, Codex |
| comet-archiverpamis/comet | Skill | 3.3k | yesterday | MIT | A | 34 | Codex |
| comet-github-issue-fixrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 71 | Claude Code, Codex |