diagnosing-baspowers

Files (14)

• SKILL.md
• analyst-common.md · prompts/
• cost-and-time.md · prompts/
• plan-adherence.md · prompts/
• quality-evidence.md · prompts/
• repeated-work.md · prompts/
• request-conflicts.md · prompts/
• similar-session.md · prompts/
• skill-timeline.md · prompts/
• stumbles.md · prompts/
• context-safety.md · references/
• session-discovery.md · references/
• case.md · templates/
• report.md · templates/

SKILL.md (first lines)

# Diagnosing Baspowers

## Overview

Pin down with your human partner what went wrong in a session, read the
transcripts on disk, and report what happened with evidence. Where
baspowers skill text contributed, quote it and propose a change: your
human partner maintains these skills and decides what changes.

**Core principle:** Every finding cites `path:line`. No citation, no
finding. Every number comes from the transcript or from a command you ran,
never from memory.

## Workflow

Create a todo per step. Step 5 runs only on its stated condition.

1. **Problem intake.** Ask one question at a time until you can write a
   statement naming the session(s), the turn range if known, what your
   partner expected, what happened, and the observable they care about
   (wall-clock, tokens, repeated actions, one specific action). "It took
   too long" is a complaint, not a problem statement.
2. **Locate.** Resolve each session to verified absolute filesystem paths using
   `references/session-discovery.md`. Confirm a past session by quoting its
   first prompt and timestamp, and list every candidate you rejected with the
   reason, or "none". Enumerate subagent transcripts. Create
   `~/.baspowers/diagnosing-baspowers/<session-id>/`, tell your
   partner the path, and fill `templates/case.md` there, following its
   provenance rules for environment and skill observations.
3. **Triage.** Read the region around the reported problem yourself. Then
   dispatch one analyst subagent per dimension in parallel, each given the
   case file path, `prompts/analyst-common.md`, and one dimension file from
   `prompts/`: `skill-timeline.md`,
   `plan-adherence.md`, `repeated-work.md`, `stumbles.md`,
   `quality-evidence.md`, `request-conflicts.md`, `cost-and-time.md`.
   Split a dimension by turn range when the transcript is long. Discard
   any returned finding without `path:line`.
4. **Report.** Fill every section of `templates/report.md` in order, write
   it to the workspace, show it, and give the path. Check what cited content
   actually proves and preserve the supporting case; a symlink alias is not a
   redundant copy.
5. **Similar sessions** — when asked. Turn confirmed findings into a
   signature, list candidates by mtime and size, find marker line numbers,
   dispatch `prompts/similar-session.md` per candidate in parallel, and
   append report §9.

## Quick reference

All seven analysts always run. This table says which region to read
yourself in step 3 and which findings to lead with in the verdict.

| Complaint | Read first, lead with |
|---|---|
| "It took too long" | cost-and-time, stumbles |
| "Why did it do this extra work?" | repeated-work, plan-adherence |
| "Why is it so expensive?" | cost-and-time |
| "What the hell is it doing?" (still running) | skill-timeline; note in-progress in coverage |
| "It ignored the plan" | plan-adherence, compaction lines first |
| "Skill X never fired" | skill-timeline |

## Hard rules

- **Context safety.** One transcript line can be a megabyte. Follow
  `references/context-safety.md` on every session file, every time.
- **Read-only.** Never modify, move, or delete a session file.
- **Exact paths to subagents.** A subagent's "current session" is its
  own. Pass absolute paths and ids.
- **Human prompts only.** Hook output, system reminders, and tool results
  are not your partner's words. In a subagent transcript, "user" is the
  parent agent.
- **Propose, don't edit.** Report §7 names the skill text involved, with
  `path:line` in the skill and in the transcript, and proposes a change.
  Never edit a skill during diagnosis; changing it is a separate task your
  partner starts.
- **Intake before analysis.** Nothing in steps 2–5 starts until your
  partner has answered. If they are away, write the questions and stop.
  A statement you reconstructed for them is not an answer. An
  already-scoped request — one specific event, what is running now, or
  the analysis to run — is itself the statement: answer it, then ask.
  A whole-session "why" is a complaint.

## Red Flags

| Thought | Reality |
|---------|---------|
| "The problem is obvious, skip intake" | The problem statement scopes everything. Ask. |
| "They're away, so I'll reconstruct the statement" | You cannot reconstruct what they wanted. Write the questions and stop. |
| "I'll sweep everything now and ask at the end" | An unscoped sweep spends their budget on the wrong question. Ask first. |
| "Small, targeted edit, I'll just fix the skill now" | Propose it in report §7. Editing the skill is a separate task your partner starts. |
| "The price per token is well known" | Numbers you did not compute from the transcript are invented. Cite or drop. |

From basnijholt/baspowers, MIT.

More from basnijholt/baspowers