claude-attribution 1.3.0 → 1.5.1

package/README.md

@@ -1,37 +1,45 @@
 # claude-attribution
 
-> **Hey team** — we've built a tool that automatically tracks and documents AI contribution in your PRs so you don't have to do it manually.
->
-> **One-time setup:**
-> ```bash
-> npm install -g claude-attribution
-> claude-attribution install ~/Code/your-repo
-> claude-attribution init --ai    # repo built with Claude Code — or --human if human/mixed
-> git add .claude/settings.json .gitignore && git commit -m "chore: install claude-attribution hooks"
-> ```
-> From then on, just work normally. After each `git commit` you'll see a one-line attribution summary in your terminal. When you're ready to open a PR, run `/pr` in Claude Code (or `claude-attribution pr "feat: your title"`) — it fills in the metrics automatically, no copy-paste needed.
->
-> **Using Copilot or @claude (claude-code-action)?** Commits made by AI bots (Copilot coding agent, `@claude` via claude-code-action) are automatically detected and attributed as 100% AI in metrics — no extra steps needed. See [AI Actor Attribution](#ai-actor-attribution-copilot-bot-claude-gha) for details. For Copilot-specific org-level stats, use the GitHub Copilot usage dashboard. Both tools' data flows into the VP Datadog dashboard automatically on every PR merge.
->
-> **Requirements:** [Bun](https://bun.sh) (preferred) or Node 18+, and `gh` (GitHub CLI) authenticated for the `/pr` command.
+AI code attribution for Claude Code. After every `git commit`, a one-line summary appears in your terminal:
+
+```
+[claude-attribution] a3f1b2c — 142 AI / 38 human / 4 mixed lines (77% AI)
+```
+
+When a PR is opened, full metrics — model usage, token counts, tool calls, and attribution percentages — are injected automatically into the PR body. No copy-paste, no manual tracking.
+
+**Quick start:**
+
+```bash
+npm install -g claude-attribution
+claude-attribution install ~/Code/your-repo
+claude-attribution init --ai    # if repo was built with Claude Code; use --human otherwise
+git add .claude/settings.json .github/workflows/claude-attribution-pr.yml .gitignore
+git commit -m "chore: install claude-attribution hooks"
+git push
+```
+
+**Using Copilot or `@claude` (claude-code-action)?** Bot commits are auto-detected and attributed as 100% AI — no extra steps needed. See [AI Actor Attribution](#ai-actor-attribution-copilot-bot-claude-gha).
+
+**Requirements:** [Bun](https://bun.sh) (preferred) or Node 18+, and `gh` (GitHub CLI) authenticated for the `/pr` command.
 
 ---
 
-AI code attribution tracking for Claude Code. Measures which lines in a commit were written by Claude vs. a human — using checkpoint snapshots and line-level SHA-256 comparison, not gross write-operation counts.
+Measures which lines in a commit were written by Claude vs. a human — using checkpoint snapshots and line-level SHA-256 comparison, not gross write-operation counts.
 
 ---
 
 ## GitHub Actions Requirements
 
-Three workflows are installed into repos that use this tool. Each requires specific GitHub Actions to be allowed in your org. If your org enforces an action allowlist, you must approve the third-party action before the workflows will run.
+Up to three workflows are installed into repos that use this tool — one always, two optionally. Each requires specific GitHub Actions to be allowed in your org. If your org enforces an action allowlist, you must approve the third-party action before the workflows will run.
 
 ### Workflows and the actions they use
 
-| Workflow file | Trigger | GitHub-owned actions | Third-party actions |
-|---|---|---|---|
-| `claude-attribution-pr.yml` | PR opened / pushed | `actions/checkout@v4`, `actions/github-script@v7` | `oven-sh/setup-bun@v2` |
-| `claude-attribution.yml` | PR merged | `actions/checkout@v4` | `oven-sh/setup-bun@v2` |
-| `claude-attribution-gha.yml` | Every push (optional) | `actions/checkout@v4` | `oven-sh/setup-bun@v2` |
+| Workflow file | Trigger | Install | GitHub-owned actions | Third-party actions |
+|---|---|---|---|---|
+| `claude-attribution-pr.yml` | PR opened / pushed | Always | `actions/checkout@v4`, `actions/github-script@v7` | `oven-sh/setup-bun@v2` |
+| `claude-attribution-export.yml` | PR merged | Optional (prompted) | `actions/checkout@v4` | `oven-sh/setup-bun@v2` |
+| `claude-attribution-gha.yml` | Every push | Optional (claude-code-action detected) | `actions/checkout@v4` | `oven-sh/setup-bun@v2` |
 
 **GitHub-owned actions** (`actions/*`) are pre-approved in all orgs by default.
 
@@ -44,7 +52,7 @@ Three workflows are installed into repos that use this tool. Each requires speci
 | Workflow | `contents` | `pull-requests` | Why |
 |---|---|---|---|
 | `claude-attribution-pr.yml` | read | write | Reads git history; writes metrics into the PR body |
-| `claude-attribution.yml` | read | — | Reads git notes and pushes Datadog metrics |
+| `claude-attribution-export.yml` | read | — | Reads git notes and exports metrics via OTLP/webhook |
 | `claude-attribution-gha.yml` | write | — | Pushes attribution git notes back to origin |
 
 ### Required secrets
@@ -52,8 +60,11 @@ Three workflows are installed into repos that use this tool. Each requires speci
 | Secret / Variable | Workflow | Required | Notes |
 |---|---|---|---|
 | `GITHUB_TOKEN` | All | Automatic | Provided by GitHub Actions; no setup needed |
-| `DATADOG_API_KEY` | `claude-attribution.yml` | Yes | Org-level secret; needed to push metrics to Datadog |
-| `DATADOG_SITE` | `claude-attribution.yml` | No | Org-level variable; defaults to `datadoghq.com` |
+| `OTEL_EXPORTER_OTLP_ENDPOINT` | `claude-attribution-export.yml` | One of these | OTLP/HTTP base URL (e.g. `https://otlp.datadoghq.com`, `https://otlp-gateway-<zone>.grafana.net/otlp`, `http://localhost:4318`). Unset = dry-run mode. |
+| `OTEL_EXPORTER_OTLP_HEADERS` | `claude-attribution-export.yml` | Depends on backend | Comma-separated `key=value` auth headers (e.g. `DD-Api-Key=xxx` for Datadog, `x-honeycomb-team=xxx` for Honeycomb) |
+| `DATADOG_API_KEY` | `claude-attribution-export.yml` | Datadog shortcut | Org-level secret; auto-configures the Datadog OTLP endpoint without needing `OTEL_EXPORTER_OTLP_ENDPOINT`. |
+| `DATADOG_SITE` | `claude-attribution-export.yml` | No | Org-level variable; used with `DATADOG_API_KEY`. Defaults to `datadoghq.com`. |
+| `METRICS_WEBHOOK_URL` | `claude-attribution-export.yml` | No | Posts a flat JSON payload to any HTTP endpoint on each PR merge. Can be used alongside OTLP. |
 
 ---
 
@@ -67,30 +78,16 @@ Three workflows are installed into repos that use this tool. Each requires speci
 
 ### One-time setup (per developer machine)
 
-**Option A — npm (recommended):**
-
 ```bash
 npm install -g claude-attribution
 ```
 
-**Option B — clone (if npm isn't available):**
-
-```bash
-git clone git@github.com:DTS-Productivity-Engineering/claude-attribution.git ~/Code/claude-attribution
-cd ~/Code/claude-attribution
-bun install
-```
-
 ### Install into a repo (per repo, per developer)
 
 **Step 1 — Run the installer:**
 
 ```bash
-# npm install:
 claude-attribution install ~/Code/your-repo
-
-# clone install:
-bun ~/Code/claude-attribution/src/setup/install.ts ~/Code/your-repo
 ```
 
 **Step 2 — Declare your attribution baseline (`init`):**
@@ -106,6 +103,9 @@ claude-attribution init --human
 
 # Not sure? Run with no flag — same as --human, prints a confirmation:
 claude-attribution init
+
+# Repo has mixed history — mark commits after a specific date as AI-written:
+claude-attribution init --ai-since 2025-01-01
 ```
 
 > **Why this matters:** Without `init`, the codebase-wide AI% starts at 0% and grows only from new commits. If your repo is all Claude Code, run `init --ai` now or the metrics will be misleading until the entire codebase has been re-committed line by line.
@@ -139,11 +139,14 @@ The installer makes the following changes to the target repo:
 
 **`.github/workflows/claude-attribution-pr.yml`** — GitHub Actions workflow that fires on every PR open and push. Injects metrics into the PR body automatically for PRs created outside Claude (Copilot, manual `gh pr create`, GitHub UI). Skips injection if the local `post-bash` hook already injected metrics on `opened`; always updates on `synchronize` (new commits).
 
+**`.github/workflows/claude-attribution-export.yml`** — fires on every PR merge. Exports AI attribution metrics via OTLP/HTTP or a generic webhook. Supports Datadog, Grafana Cloud, Splunk Observability, New Relic, Honeycomb, and any OpenTelemetry Collector. Runs in dry-run mode (prints payload to stdout, exits 0) when no export destination is configured. See [Metrics Export](#metrics-export).
+
 **`.github/workflows/claude-attribution-gha.yml`** *(optional — installed when claude-code-action is detected)* — fires on every push. Writes a 100% AI git note for commits made by known AI actors (e.g. `@claude` via claude-code-action, Copilot coding agent). Silent no-op for human commits. See [AI Actor Attribution](#ai-actor-attribution-copilot-bot-claude-gha).
 
-**`.claude/commands/`** — installs two slash commands:
+**`.claude/commands/`** — installs three slash commands:
 - `/metrics` — generate a PR metrics report
-- `/start` — mark the start of a new Jira ticket session
+- `/start` — mark the start of a new ticket session
+- `/pr` — create a PR with metrics embedded
 
 **`.gitignore`** — adds `.claude/logs/` so tool usage logs don't end up in version control.
 
@@ -177,16 +180,12 @@ claude-attribution init --ai     # only if repo was built 100% with Claude Code
 git push origin refs/notes/claude-attribution-map
 ```
 
-### Re-installing after moving this directory
+### Re-installing
 
-If you move `~/Code/claude-attribution` to a different path, re-run the installer — it updates the absolute paths in `settings.json` and the git hook:
+If you reinstall `claude-attribution` globally (e.g. after upgrading), re-run the installer — it updates the absolute paths in `settings.json` and the git hook:
 
 ```bash
-# npm install:
 claude-attribution install ~/Code/your-repo
-
-# clone install:
-bun src/setup/install.ts ~/Code/your-repo
 ```
 
 ### Uninstalling
@@ -194,14 +193,10 @@ bun src/setup/install.ts ~/Code/your-repo
 To remove claude-attribution from a repo:
 
 ```bash
-# npm install:
 claude-attribution uninstall ~/Code/your-repo
-
-# clone install:
-bun ~/Code/claude-attribution/src/setup/uninstall.ts ~/Code/your-repo
 ```
 
-This removes hooks from `.claude/settings.json`, removes `.git/hooks/post-commit`, removes the slash commands, removes `.github/workflows/claude-attribution-pr.yml`, and removes any legacy `pre-push` hooks (for example `.husky/pre-push` or `.git/hooks/pre-push`) if present. Attribution state (`.claude/attribution-state/`) and logs (`.claude/logs/`) are left in place. The `remote.origin.push` refspec is also removed from git config.
+This removes hooks from `.claude/settings.json`, removes `.git/hooks/post-commit`, removes the slash commands, removes `.github/workflows/claude-attribution-pr.yml`, `.github/workflows/claude-attribution-export.yml`, and `.github/workflows/claude-attribution-gha.yml` (if present), and removes any legacy `pre-push` hooks (for example `.husky/pre-push` or `.git/hooks/pre-push`) if present. Attribution state (`.claude/attribution-state/`) and logs (`.claude/logs/`) are left in place. The `remote.origin.push` refspec is also removed from git config.
 
 ---
 
@@ -237,33 +232,36 @@ Metrics are injected automatically — no command needed.
 
 **On every new push to an open PR**: the workflow fires on `synchronize` and updates the attribution percentages to reflect new commits.
 
-The metrics block looks like (when the cumulative minimap exists):
+The metrics block injected into the PR body looks like (when the cumulative minimap exists):
 
-```markdown
-## Claude Code Metrics
-
-**Codebase: ~77% AI** (3200 / 4150 lines)
-**This PR:** 184 lines changed (4% of codebase) · 77% Claude edits · 142 AI lines · Active: 8m
+> ## Claude Code Metrics
+>
+> **Codebase: ~77% AI** (3200 / 4150 lines)
+> **This PR:** 184 lines changed (4% of codebase) · 77% Claude edits · 142 AI lines · Active: 8m
+>
+> | Model | Calls | Input | Output | Cache |
+> |-------|-------|-------|--------|-------|
+> | Sonnet | 45 | 120K | 35K | 10K |
+> | **Total** | 45 | 120K | 35K | 10K |
+>
+> **Human prompts (steering effort):** 12
+>
+> <details><summary>Tools · Agents · Files</summary>
+>
+> **Tools:** Edit ×47, Read ×31, Bash ×12
+>
+> </details>
 
-| Model | Calls | Input | Output | Cache |
-|-------|-------|-------|--------|-------|
-| Sonnet | 45 | 120K | 35K | 10K |
-| **Total** | 45 | 120K | 35K | 10K |
+Before running `init --ai` (or on a fresh install with no minimap), the headline falls back to the session-only view:
 
-**Human prompts (steering effort):** 12
+> **AI contribution: ~77%** (142 of 184 committed lines) · Active: 8m
 
-<details>
-<summary>Tools · Agents · Files</summary>
+The block is wrapped in HTML comments for idempotent updates — re-running replaces the existing block rather than appending:
 
-**Tools:** Edit ×47, Read ×31, Bash ×12
-...
-</details>
 ```
-
-Before running `init --ai` (or on a fresh install with no minimap), the headline falls back to the session-only view:
-
-```markdown
-**AI contribution: ~77%** (142 of 184 committed lines) · Active: 8m
+<!-- claude-attribution metrics -->
+...metrics content...
+<!-- /claude-attribution metrics -->
 ```
 
 #### Manual option
@@ -271,7 +269,7 @@ Before running `init --ai` (or on a fresh install with no minimap), the headline
 If you need to create a PR with metrics outside of Claude, use the `/pr` slash command or CLI directly:
 
 ```bash
-claude-attribution pr "feat: COMM-1234 add user authentication"
+claude-attribution pr "feat: PROJ-1234 add user authentication"
 claude-attribution pr "feat: my feature" --draft
 claude-attribution pr "feat: my feature" --base develop
 ```
@@ -284,7 +282,6 @@ To see the metrics output without creating a PR, use `/metrics` or run directly:
 
 ```bash
 claude-attribution metrics
-# or: bun ~/Code/claude-attribution/src/metrics/calculate.ts
 ```
 
 The output is markdown you paste into your PR description:
@@ -351,7 +348,7 @@ Example output:
 {
   "commit": "a3f1b2c",
   "session": "abc-123-...",
-  "branch": "feature/COMM-1234",
+  "branch": "feature/PROJ-1234",
   "timestamp": "2026-03-26T15:32:00.000Z",
   "files": [
     { "path": "src/components/Foo.tsx", "ai": 82, "human": 10, "mixed": 2, "total": 94, "pctAi": 87 }
@@ -466,36 +463,60 @@ To force re-detection of the TypeScript runtime (e.g., after installing Bun): `r
 
 ---
 
-## VP Dashboard (Datadog)
+## Metrics Export
 
-Attribution data is pushed to Datadog automatically on every PR merge via GitHub Actions (`.github/workflows/claude-attribution.yml`). No developer holds the API key — it lives in an org-level GHA secret.
+Attribution metrics are exported automatically on every PR merge via GitHub Actions (`.github/workflows/claude-attribution-export.yml`). The workflow uses the OpenTelemetry OTLP/HTTP JSON format and supports any OTel-compliant backend.
 
-**Metrics pushed on each merged PR:**
+**Metrics exported on each merged PR:**
 
-| Metric | Description |
-|--------|-------------|
-| `claude_attribution.ai_lines` | Lines written by Claude and committed unchanged |
-| `claude_attribution.human_lines` | Lines written or left unchanged by the developer |
-| `claude_attribution.total_lines` | Total committed lines in the PR |
-| `claude_attribution.pct_ai` | Percentage of lines attributed to Claude (this PR) |
-| `claude_attribution.codebase_pct_ai` | Cumulative codebase-wide AI% at PR merge time (requires minimap) |
-| `claude_attribution.codebase_total_lines` | Total codebase lines tracked in the minimap |
-| `github_copilot.acceptance_rate` | Org-level Copilot suggestion acceptance rate |
-| `github_copilot.lines_accepted` | Copilot lines accepted org-wide |
-| `github_copilot.lines_suggested` | Copilot lines suggested org-wide |
+| Metric | Unit | Description |
+|--------|------|-------------|
+| `claude_attribution.ai_lines` | lines | Lines written by Claude and committed unchanged |
+| `claude_attribution.human_lines` | lines | Lines written or left unchanged by the developer |
+| `claude_attribution.total_lines` | lines | Total committed lines in the PR |
+| `claude_attribution.pct_ai` | % | Percentage of lines attributed to Claude (this PR) |
+| `claude_attribution.codebase_pct_ai` | % | Cumulative codebase-wide AI% at PR merge time (requires minimap) |
+| `claude_attribution.codebase_total_lines` | lines | Total codebase lines tracked in the minimap |
+| `claude_attribution.cost_usd` | $ | Estimated Claude API cost for this PR (requires v1.5.0+ notes) |
+| `claude_attribution.input_tokens` | tokens | Total input tokens consumed by Claude in this PR |
+| `claude_attribution.output_tokens` | tokens | Total output tokens generated by Claude in this PR |
+| `claude_attribution.cache_read_tokens` | tokens | Cache read tokens in this PR |
+| `claude_attribution.cache_creation_tokens` | tokens | Cache creation tokens in this PR |
 
-All metrics are tagged `repo:`, `pr:`, `branch:`, `author:`, `tool:` — enabling side-by-side Claude vs. Copilot comparison on a single dashboard.
+Token and cost metrics are only emitted when the git notes contain token data (written by v1.5.0+ hooks). All metrics carry attributes `pr`, `branch`, `author`, `tool` — enabling per-PR trend analysis.
 
-> **Important limitation — Copilot metrics are org-level aggregates, not per-PR or per-developer:**
-> GitHub's Copilot usage API returns org-wide daily totals (suggestions shown, lines accepted, acceptance rate). These are the same numbers regardless of which PR triggered the push. The Copilot rows in Datadog reflect organization-wide Copilot activity at the time of the push — they cannot be scoped to a specific PR, branch, or developer. In contrast, `claude_attribution.*` metrics are per-PR and per-file, derived from git notes written at commit time.
->
-> If you need per-seat or per-repo Copilot breakdowns, use the GitHub Copilot usage dashboard directly. The org-level Copilot numbers here are useful as a trend signal alongside Claude attribution data.
+**Supported backends:**
+
+| Backend | Configuration |
+|---------|---------------|
+| **Datadog** (shortcut) | Set `DATADOG_API_KEY` secret (and optionally `DATADOG_SITE` org variable, defaults to `datadoghq.com`). Endpoint is auto-configured. |
+| **Datadog** (explicit) | `OTEL_EXPORTER_OTLP_ENDPOINT=https://otlp.datadoghq.com`, `OTEL_EXPORTER_OTLP_HEADERS=DD-Api-Key=<key>` |
+| **Grafana Cloud** | `OTEL_EXPORTER_OTLP_ENDPOINT=https://otlp-gateway-<zone>.grafana.net/otlp`, `OTEL_EXPORTER_OTLP_HEADERS=Authorization=Basic <base64(user:token)>` |
+| **Splunk Observability** | `OTEL_EXPORTER_OTLP_ENDPOINT=https://ingest.<realm>.signalfx.com/v2/datapoint/otlp`, `OTEL_EXPORTER_OTLP_HEADERS=X-SF-Token=<token>` |
+| **New Relic** | `OTEL_EXPORTER_OTLP_ENDPOINT=https://otlp.nr-data.net`, `OTEL_EXPORTER_OTLP_HEADERS=api-key=<key>` |
+| **Honeycomb** | `OTEL_EXPORTER_OTLP_ENDPOINT=https://api.honeycomb.io`, `OTEL_EXPORTER_OTLP_HEADERS=x-honeycomb-team=<key>` |
+| **OTel Collector** | `OTEL_EXPORTER_OTLP_ENDPOINT=http://your-collector:4318` |
+| **Generic webhook** | `METRICS_WEBHOOK_URL=https://...` — POSTs a flat JSON payload with `pr`, `repo`, `author`, `branch`, `ai_lines`, `human_lines`, `total_lines`, `pct_ai`, and optionally `codebase_pct_ai` / `codebase_total_lines` / `cost_usd` / `input_tokens` / `output_tokens` |
 
-**Required secrets (set once at org level):**
-- `DATADOG_API_KEY` — Datadog API key
-- `DATADOG_SITE` variable — e.g. `datadoghq.com`
+When no destination is configured, the workflow runs in **dry-run mode** — it prints the OTLP payload to stdout and exits 0. This makes it safe to install and test before secrets are set.
+
+Set secrets at the org level so they apply to all repos that use this tool. Multiple export destinations can be active simultaneously (e.g. both `OTEL_EXPORTER_OTLP_ENDPOINT` and `METRICS_WEBHOOK_URL`).
+
+**Model pricing (org variables — update when Anthropic changes pricing):**
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `CLAUDE_PRICE_OPUS_INPUT` | `15.00` | $ per 1M input tokens (Claude Opus) |
+| `CLAUDE_PRICE_OPUS_OUTPUT` | `75.00` | $ per 1M output tokens (Claude Opus) |
+| `CLAUDE_PRICE_SONNET_INPUT` | `3.00` | $ per 1M input tokens (Claude Sonnet) |
+| `CLAUDE_PRICE_SONNET_OUTPUT` | `15.00` | $ per 1M output tokens (Claude Sonnet) |
+| `CLAUDE_PRICE_HAIKU_INPUT` | `0.80` | $ per 1M input tokens (Claude Haiku) |
+| `CLAUDE_PRICE_HAIKU_OUTPUT` | `4.00` | $ per 1M output tokens (Claude Haiku) |
+| `CLAUDE_PRICE_CACHE_READ_MULT` | `0.1` | Fraction of input price for cache reads |
+| `CLAUDE_PRICE_CACHE_WRITE_MULT` | `1.25` | Fraction of input price for cache writes |
+
+Unrecognized model names (new Claude releases) fall back to Opus pricing. Set these as org-level **variables** (not secrets) — they're not sensitive.
 
-**Future:** When Faros is purchased, ADMPLAT-9609 will provide a Faros pipeline. Switching destinations is a one-line change to `src/export/pr-summary.ts` — the data collection, notes format, and GHA trigger all stay the same.
 
 ---
 
@@ -553,7 +574,7 @@ permissions:
 jobs:
   note-ai-commit:
     name: Record AI actor commit attribution
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-latest   # replace with your self-hosted runner label if needed
     steps:
       - uses: actions/checkout@v4
         with:
@@ -563,6 +584,11 @@ jobs:
       - name: Fetch attribution notes
         run: git fetch origin refs/notes/claude-attribution:refs/notes/claude-attribution || true
 
+      - name: Configure git identity for notes
+        run: |
+          git config user.email "claude-attribution[bot]@users.noreply.github.com"
+          git config user.name "claude-attribution[bot]"
+
       - uses: oven-sh/setup-bun@v2
 
       - name: Install claude-attribution
@@ -621,7 +647,7 @@ Each hook invocation is a short-lived process that exits immediately. The trace
 
 The post-commit hook may not have run. Check:
 1. Is `bun` (or `tsx`) on your PATH in a git hook context? Run `which bun` from your shell, then check if that path is in `.git/hooks/post-commit`.
-2. Did you run `bun src/setup/install.ts <repo>` for this specific repo?
+2. Did you run `claude-attribution install <repo>` for this specific repo?
 3. Check `.claude/logs/attribution.jsonl` — if it's empty, the hook isn't firing.
 
 **Attribution is 0% AI even though Claude wrote everything**

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "claude-attribution",
-	"version": "1.3.0",
+	"version": "1.5.1",
 	"description": "AI code attribution tracking for Claude Code sessions — checkpoint-based line diff approach",
 	"type": "module",
 	"bin": {

package/src/attribution/commit.ts

@@ -34,6 +34,7 @@ import {
 	type LineAttribution,
 	hashLine,
 } from "./differ.ts";
+import { parseTranscript } from "../metrics/transcript.ts";
 import {
 	writeNote,
 	headSha,
@@ -146,6 +147,21 @@ async function main() {
 		totals: aggregateTotals(fileResults),
 	};
 
+	// Attach token usage from the Claude session transcript (non-fatal if unavailable)
+	if (sessionId) {
+		const tx = await parseTranscript(sessionId, repoRoot).catch(() => null);
+		if (tx && tx.byModel.length > 0) {
+			result.modelUsage = tx.byModel.map((m) => ({
+				modelFull: m.modelFull,
+				modelShort: m.modelShort,
+				inputTokens: m.inputTokens,
+				outputTokens: m.outputTokens,
+				cacheCreationTokens: m.cacheCreationTokens,
+				cacheReadTokens: m.cacheReadTokens,
+			}));
+		}
+	}
+
 	// Write git note
 	await writeNote(result, repoRoot);
 

package/src/attribution/differ.ts

@@ -21,6 +21,16 @@ export interface FileAttribution {
 	pctAi: number;
 }
 
+/** Token usage captured from the Claude session transcript at commit time. */
+export interface CommitModelUsage {
+	modelFull: string;
+	modelShort: "Opus" | "Sonnet" | "Haiku" | "Unknown";
+	inputTokens: number;
+	outputTokens: number;
+	cacheCreationTokens: number;
+	cacheReadTokens: number;
+}
+
 export interface AttributionResult {
 	commit: string;
 	/** Session ID from .claude/attribution-state/current-session, or null if committed outside a Claude session. */
@@ -30,6 +40,8 @@ export interface AttributionResult {
 	timestamp: string;
 	files: FileAttribution[];
 	totals: Omit<FileAttribution, "path">;
+	/** Token usage from the Claude session that produced this commit. Absent for commits outside a Claude session or pre-v1.5.0 notes. */
+	modelUsage?: CommitModelUsage[];
 }
 
 /**

package/src/cli.ts

@@ -33,6 +33,9 @@ switch (cmd) {
 	case "note-ai-commit":
 		await import("./commands/note-ai-commit.ts");
 		break;
+	case "pr-summary":
+		await import("./export/pr-summary.ts");
+		break;
 	case "init":
 		await import("./commands/init.ts");
 		break;
@@ -97,6 +100,7 @@ Commands:
   pr [title]       Create PR with metrics embedded (--draft, --base <branch>)
   init [--ai | --ai-since <YYYY-MM-DD>]  Set attribution baseline in the cumulative minimap
   note-ai-commit [sha] [--push] [--if-ai-actor]  Write 100% AI git note for a commit (GHA use)
+  pr-summary           Export PR attribution metrics via OTLP/webhook (GHA use)
   start            Mark session start for per-ticket scoping
   hook <name>      Run an internal hook (used by installed git hooks)
   version          Print version