adjohn/pstack/reflect

Reflect

Mine the current conversation for durable learnings, then route them into skill edits.

Invoke when the user says "reflect" or "/reflect". Skip when the conversation is trivial, off-topic, or already covered by an existing skill the parent followed correctly. One-offs are not learnings.

1. Locate the active transcript

Before fanning out, find this conversation's transcript under ~/.claude/projects/<slug>/ (one .jsonl per session with one JSON message per line, where <slug> is the absolute working directory, symlinks resolved, with every character that is not a letter or digit, including /, ., and _, replaced by -, so /Users/you/proj becomes -Users-you-proj). Derive the directory from the current working directory. Do not glob across ~/.claude/projects/*/. That crosses workspace boundaries and reads private chats from unrelated projects.

ls -t ~/.claude/projects/<slug>/*.jsonl 2>/dev/null | head -10

There is one flat <session-uuid>.jsonl per session, and its subagents write under <session-uuid>/subagents/. For each candidate, read the first JSONL lines. Take the file whose earliest user message contains the conversation's opening user prompt. If none matches, pass a tight digest of the session instead.

2. Spawn three reviewers in parallel

One message, three Agent calls, subagent_type: general-purpose. Reviewers need MCP access to look up the tickets, chat threads, and observability traces the transcript references. Subagents inherit MCP tools by default.

Each reviewer and the synthesizer name a role line in ~/.claude/pstack-models.md and a default. Set model to that line's value, or to the default if the file or the line is missing. Leave model unset when the value is auto or inherit-parent. If the Agent tool rejects a slug, use the default and say so. If it rejects the default, use the nearest Claude tier from its error message. Pick each subagent's reasoning level (the Agent effort) for the job, per the Subagents section of the poteto-mode skill.

Configured values come from ~/.claude/pstack-models.md when present; otherwise use the inline defaults. Pass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in the Agent response body.

3. Synthesize

One Agent call, subagent_type: general-purpose, model from the reflect judgment, divergent, synthesizer line (default opus). It spot-verifies citations through MCP. Subagents inherit MCP tools by default. Pass references/synthesizer.md verbatim, with each reviewer's full output inlined where marked. It returns an Accepted / Rejected / Backlog list.

4. Structural enforcement check

Move any Accepted item that a lint rule, script, metadata flag, or runtime check would enforce more reliably to Backlog. See the encode-lessons-in-structure principle skill.

5. Apply

Present the synthesizer's full Accepted / Rejected / Backlog output and wait for explicit approval before applying any Accepted edit. The user picks the subset and may redirect routings. Skill changes affect every future agent in the org. Do not auto-apply.

File each Backlog item to your team's devex or backlog tracker without waiting. Only the Accepted list waits for approval.

Never edit a skill under plugins/cache/. Before approval, show its destination, .claude/skills/<skill>/ or ~/.claude/skills/<skill>/. After approval, copy the skill folder there and edit the copy. Never open a PR or push.

Follow each approved row's Routing exactly:

• Trivial existing-skill edit (a one-line bullet, a tightened sentence, a stale fact corrected): the parent does it directly.
• Substantive existing-skill edit (a new section, a new pattern table, more than ~10 lines): hand to the skill-creator skill if installed (from anthropics/skills) and run its draft / test / iterate loop; otherwise the parent drafts the section directly.
• tune description: <skill path> (the skill exists but didn't trigger when it should have): hand to skill-creator and run its description-optimization loop, or tune the description directly if it isn't installed.
• new skill via skill-creator: <kebab-name>: hand creation to skill-creator if installed; otherwise author the SKILL.md directly. Do not invent the shape ad hoc.

If your environment ships a SKILL.md validator, run it on every touched skill before declaring done.

6. Summarize for the user

Short list, no preamble:

• Edits applied: <skill path>. What changed, one line each.
• New skills created: <skill path>. One line each (rare).
• Backlog filed to the devex tracker: <issue title> (<tags>). One line each.
• Dropped: one line per rejected finding + reason from the synthesizer.