Borrowing it
Nothing to install: this file belongs to xiaojilele-glitch/WhyBuddy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xiaojilele-glitch/WhyBuddy/main/.kiro/steering/autopilot-five-spec-series-closure-2026-05-24.mdgit clone --depth 1 https://github.com/xiaojilele-glitch/WhyBuddyWrote 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/instructions/xiaojilele-glitch/whybuddy/autopilot-five-spec-series-closure-2026-05-24)<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/autopilot-five-spec-series-closure-2026-05-24"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/autopilot-five-spec-series-closure-2026-05-24/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/instructions/xiaojilele-glitch/whybuddy/autopilot-five-spec-series-closure-2026-05-24"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/autopilot-five-spec-series-closure-2026-05-24.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 | $0.00309 | $0.00309 |
| Opus 5.5 | $0.00124 | $0.00124 |
| Sonnet 5.5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
WhyBuddy autopilot-five-spec-series-closure-2026-05-24.md 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 1mo 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
Autopilot Five-Spec Series Closure - 2026-05-24
Scope
This steering record closes the current five-spec Autopilot series as one bounded delivery track:
autopilot-asset-staleness-modelautopilot-replan-and-branch-actionautopilot-stage-edit-modeautopilot-stage-version-historyautopilot-stage-state-coordination
Closure Rule
The five specs above are now treated as a completed series for architecture and requirement evolution purposes.
Future expansion SHALL be started through a new spec series. Future work SHALL NOT back-edit the requirements, task intent, or architectural boundaries of this five-spec series to introduce new scope.
Remaining Gates
Any remaining unchecked items in the five tasks.md files are verification, PR checklist, or manual/browser closure gates. They do not reopen the series scope and should be closed by evidence, not by changing the spec requirements.
Boundaries That Stay Locked
- Asset staleness remains a downstream artifact invalidation model, not a persistence or socket layer.
- Replan and branch actions remain explicit user-triggered flows, not background auto-branching.
- Stage edit mode remains page-one inline correction plus downstream stale marking, not a full undo stack.
- Version history remains a read-oriented family view with active-job switching, not a backend mutation model.
- Stage state coordination remains a frontend coordination layer, not a backend job-stage writer.
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.
- 1mo ago First seen · 34 lines · 309 tokens per session scan A f9149cd9bb9b
WhyBuddy autopilot-five-spec-series-closure-2026-05-24.md is an instructions file published in the GitHub repository xiaojilele-glitch/WhyBuddy (380 stars, last pushed 1mo ago), licensed MIT. It adds 309 tokens to every session, about $0.0012 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 2026-09-23.
WhyBuddy autopilot-five-spec-series-closure-2026-05-24.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| WhyBuddy autopilot-five-spec-series-closure-2026-05-24.mdxiaojilele-glitch/WhyBuddy | Instructions file | 380 | 1mo ago | MIT | A | 309 | Kiro |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |