show-me-your-work

Show me your work

Keep one canonical log.

The format

A single TSV file, one row per decision. Cells stay single-line. Evidence is a pointer, not prose. The header row is:

ts	phase	decision	why	evidence	result

• ts. ISO8601 timestamp.
• phase. The phase or workstream.
• decision. What was chosen or done, one line.
• why. The reason in plain words. If a principle drove it, say it plainly, not as a jargon tag.
• evidence. A link or path that proves it: commit SHA, PR number, file:line, or an artifact or screenshot path. Never a paragraph.
• result. The outcome or predicate state: tests green, reverted, INCONCLUSIVE, open.

An example, plain-spoken so a reviewer reads it at a glance.

ts	phase	decision	why	evidence	result
2026-05-24T09:02:00Z	frame	counted the work first, 40 resources still on the old inventory exports	wanted to know the size before starting a long run	commit 3a9f1c2	found 3 resources that wrap the exports in their own bridge
2026-05-24T09:40:00Z	harness	wrote a script listing every call to the old exports before changing anything	so we can compare old against new and catch a missed call	scripts/find-old-exports.sh	baseline of 212 calls saved
2026-05-24T11:15:00Z	shops	moved the shop resource to the new exports	keep each resource's change small and checkable on its own	commit 7c21e0a	0 old calls left in shops, lua-language-server --check clean
2026-05-24T12:30:00Z	garages	threw out a helper's work because it skipped two files	checked the real diff instead of trusting its summary	worktree reset	reverted, tightened the instructions for next time

Logging a row

Write each entry the way you'd tell a teammate what you did: plain words, concrete actions, no jargon.

Use the helper scripts/log.sh <logfile> <phase> <decision> <why> <evidence> <result> from this skill's directory. It stamps ts, writes the header on first use, strips stray tabs and newlines, and prefixes any cell starting with =, +, -, or @ with a single quote so a spreadsheet doesn't run it as a formula. A bare printf appending a row works too, but mind those same bytes if cells come from generated or user-supplied text.

Log decision points and checkpoints, not every action: a fork chosen, a unit completed with its verification result, a pivot or revert with its trigger, a blocker surfaced, a gate fixed. For loop runs, one row per iteration. Skip the trivial and self-evident.

A run is one agent conversation, including its later turns and any summary of it. A pickup, a replacement agent, or a new chat starts a new run. When a run adds to a log that already has rows, its first row has phase start, and so does its first row after another run's start row. So a run that comes back to a log in a later turn first reads the log's last rows to see whether another run wrote since. A start row names the ts range of the rows before it that this run did not write, and its evidence names this run, such as its session id. Use phase start for nothing else.

Where it lives

By default the log is a working artifact, not committed. Keep it at decisions.tsv in the work dir, or .audit/<task-slug>.tsv when several efforts run at once, and leave it out of git.

Commit it only when the work is ambitious enough that a reviewer needs the trail to trust the result.

Rules

• Append-only. A wrong call gets a new row that supersedes it. Never edit or delete history.
• Prefer evidence produced by committed scripts over hand-made one-offs, per Encode Lessons in Structure (in the principles skill).

Audit the log against the transcript

At the end of the run, before handing back, check the log told the truth. Read this run's transcript: in Claude Code, the session's .jsonl file under ~/.claude/projects/; in Codex, its file under ~/.codex/sessions/; in T3 Code, t3_thread_read with view: "activity", following nextPosition until hasMore is false. Find the session by searching for this run's opening prompt. Read only this run's session: other sessions hold unrelated private chats. Walk this run's rows against what actually happened. Each stretch of them begins at one of this run's start rows, or at the first row if this run created the log, and ends at the next start row of another run:

• Check that every row maps to a real decision or action.
• Check that each row's evidence resolves and shows what the row claims.
• A fork, pivot, or abandoned approach that shaped the work but isn't logged is a gap. Add it.

Correct the log, not the story. The audit never edits or removes a row, even an invented one. When a row records neither a real decision nor a real action, or its claim or evidence is wrong, add a row that supersedes it with what actually happened and a pointer that resolves. This audit does not check rows outside this run's stretches. If this run's own work shows one of them is wrong, supersede it like any wrong call.

Cross-model review of the trail

Before handing back, start one subagent named Trail reviewer on the review line of ~/.config/ox/models.md. If that line names the model that did the work, use a panel entry from a different model family instead: self-review is not a substitute. If neither gives a different model, run it on your own model and say so in the Attention section. Its brief gives the log's absolute path and the transcript's location, and says "read-only: inspect only, no writes, no git commands" and "Do not delegate". It reads the trail and the transcript, then flags what the user should pay attention to. Not a redo of the work, a scan for what's suboptimal or risky:

• Decisions logged with weak or absent evidence.
• Verification steps skipped or claimed without proof in the transcript.
• Choices that look risky in hindsight (premature, scope-creeping, papering over a symptom).
• Gaps the user would otherwise miss on a casual skim.

Every reply for a run that produced a trail ends with an "Attention" section. Lead with the reviewer's model on its own line (reviewed by <model>), then list each flag pointing to specific rows or moments. "No flags" is a valid value. The model name is not.

Reviewing the trail

Read top to bottom, follow the evidence pointers, spot-check. GitHub renders a committed TSV as a table. column -s$'\t' -t decisions.tsv renders it in a terminal.

Composing this skill

Other skills route their audit trail here instead of inventing one. Reference it by name and let it own the format. Don't restate the columns.