Individual skill
why
Explain why code exists in its current form by sending one investigator to each reachable evidence source and returning a cited, confidence-graded answer. Use for "why does this exist", "why was it built this way", "where did this limit come from", "is this dead code".
plugins/requie/endostack/skills/why/SKILL.md
Source commit d780783eba4ecc7c8b9429f95c9362df95f07c61
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,532
- Repository last updated
- Nov 6, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-coding Repository topic
- awesome Repository topic
- awesome-list Repository topic
- codex Repository topic
- codex-plugins Repository topic
- openai Repository topic
- codex-skill Repository topic
- codex-skills Repository topic
- marketplace Repository topic
- codex-marketplace Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 10,839 bytesSKILL.mdcore · 10,839 bytesSKILL.mdcore · 10,839 bytesSKILL.mdcore · 10,839 bytesSKILL.mdcore · 10,839 bytesreferences/epistemics.mddoc · 6,171 bytesreferences/investigator-brief.mddoc · 5,111 bytesreferences/source-index.mddoc · 2,349 bytesreferences/sources/code-archaeology.mddoc · 3,604 bytesreferences/sources/databricks.mddoc · 6,313 bytesreferences/sources/datadog.mddoc · 4,518 bytesreferences/sources/incident-postmortem.mddoc · 1,169 bytesreferences/sources/linear.mddoc · 3,361 bytesreferences/sources/notion.mddoc · 3,134 bytesreferences/sources/sentry.mddoc · 3,359 bytesreferences/sources/slack.mddoc · 2,873 bytesreferences/synthesizer-brief.mddoc · 5,714 bytes
Read excerpt
# why
Code shows what a system does. The reason it does it that way lives in commit messages, PR threads, tickets, design docs, chat, dashboards, error trackers and warehouse tables, and each of those records is partial. You answer a "why" question by searching every source you can reach in parallel, one investigator per source, then handing all of the evidence to a single synthesizer that grades each claim by how well it is supported. The user gets an answer that separates what someone wrote down from what you inferred and from what nobody recorded.
Start this skill on an explicit user request, such as typing `/why`, and never on your own initiative. Other skills call it internally: [teach](../teach/SKILL.md) uses it for the motivation half of an explanation, [recall](../recall/SKILL.md) reuses its investigators with a present-tense question, and [blast-radius](../blast-radius/SKILL.md) reuses its anchor step.
## Questions this skill answers
- Why a piece of code, pattern, feature or named design decision exists or looks the way it does.
- Which alternative the team picked and what it gave up.
- The history of a regression, the background of a postmortem, where a constant or limit came from (numbers are often taken from data).
- Whether suspected dead code still has a reason to exist, and why it was added.
- Broad historical surveys of an area.