skiplevel 1.1.0__tar.gz

skiplevel-1.1.0/.gitignore

@@ -0,0 +1,14 @@
+__pycache__/
+*.pyc
+*.egg-info/
+dist/
+build/
+.venv/
+venv/
+360-review.html
+360-review.json
+skiplevel-report.html
+skiplevel-report.json
+_autoscroll.html
+.claude/
+.repowise/

skiplevel-1.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Repowise
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

skiplevel-1.1.0/PKG-INFO

@@ -0,0 +1,227 @@
+Metadata-Version: 2.4
+Name: skiplevel
+Version: 1.1.0
+Summary: Have a skip-level with your coding agents: The 360 Review, a two-sided performance review generated locally from your own transcripts.
+Project-URL: Homepage, https://github.com/repowise-dev/skiplevel
+Project-URL: Issues, https://github.com/repowise-dev/skiplevel/issues
+Author: Repowise
+License-Expression: MIT
+License-File: LICENSE
+Keywords: analytics,claude,claude-code,cli,codex,coding-agent,opencode,skiplevel
+Classifier: Environment :: Console
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development
+Requires-Python: >=3.10
+Requires-Dist: jinja2>=3.0
+Description-Content-Type: text/markdown
+
+<div align="center">
+
+# skiplevel
+
+**Have a skip-level with your coding agents.**
+
+[![PyPI](https://img.shields.io/pypi/v/skiplevel?style=flat-square&logo=pypi&logoColor=white&label=pypi&color=6f54d6)](https://pypi.org/project/skiplevel/)
+[![Python](https://img.shields.io/pypi/pyversions/skiplevel?style=flat-square&logo=python&logoColor=white&color=4c8bf5)](https://pypi.org/project/skiplevel/)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue?style=flat-square)](LICENSE)
+[![Runs 100% local](https://img.shields.io/badge/runs-100%25_local-22c55e?style=flat-square)](#privacy)
+[![Agents](https://img.shields.io/badge/agents-Claude_Code_·_Codex_·_opencode-f59e0b?style=flat-square)](#supported-agents)
+
+<img src="https://raw.githubusercontent.com/repowise-dev/skiplevel/main/docs/hero.gif" alt="The 360 Review — a sample skiplevel report scrolling through the agent's scorecard" width="860">
+
+</div>
+
+You meet with the agent. The agent meets with you. Management hears both
+sides. skiplevel turns the transcripts already sitting on your machine
+into **The 360 Review**: a two-sided performance review between you and
+your coding agents — Claude Code, Codex CLI, and opencode. HR regrets
+scheduling the meeting.
+
+```
+$ uvx skiplevel
+
+skiplevel: scheduling a meeting with Claude Code + opencode's managers...
+  rifling through ~/.claude/projects ...
+  rifling through ~/.local/share/opencode ...
+  found 652 sessions (432 MB). Reading everything. Judging silently.
+  parsed 541 sessions across 31 days...
+  counted 52 'you're absolutely right's... oh no
+  tallied 34,849 tool calls and $4,062.61 in tokens...
+  found one file read 30 times in a single session. no further questions.
+  verdict: AGENT A- / YOU B. the committee has spoken.
+
+Skip-level complete in 8.1s. The truth is in skiplevel-report.html
+generated locally. nothing left your machine.
+```
+
+One self-contained HTML file. Four themes: midnight (dark, default),
+paper (printed HR document), terminal (green phosphor), and tabloid
+(newsprint gossip). Switchable from a pill in the report, persistent,
+and exports respect the active theme. Looks good in screenshots, which
+is the point.
+
+## Quickstart
+
+```bash
+uvx skiplevel          # zero install, zero config
+# or
+pip install skiplevel
+skiplevel
+```
+
+Flags:
+
+| flag        | what it does                                            |
+|-------------|---------------------------------------------------------|
+| `--harness H` | `auto` (default: review every agent with transcripts), `claude-code`, `codex`, or `opencode` |
+| `--dir PATH`  | transcripts root (default: each harness's own home)    |
+| `--out PATH`  | output file (default `./skiplevel-report.html`)        |
+| `--json`      | also dump the raw stats JSON next to the HTML          |
+| `--no-open`   | do not open a browser                                  |
+| `--roast`     | opt-in LLM roast via your own `claude` CLI (see below) |
+| `--theme T`   | initial theme: `midnight`, `paper`, `terminal`, `tabloid` |
+
+## Supported agents
+
+| harness     | where the diary lives                                       |
+|-------------|-------------------------------------------------------------|
+| Claude Code | `~/.claude/projects/**/*.jsonl`                             |
+| Codex CLI   | `$CODEX_HOME/sessions/` and `archived_sessions/` rollout JSONL (default `~/.codex`) |
+| opencode    | `~/.local/share/opencode/opencode.db` (SQLite), or the older `storage/` JSON tree |
+
+By default every harness with transcripts gets summoned into the same
+meeting and one combined review. `--harness codex` (or `claude-code`,
+`opencode`) reviews a single agent; `--dir` points at a non-standard
+location, and the layout is sniffed automatically.
+
+Notes per harness:
+
+- **Codex CLI**: archived copies of active sessions are deduplicated,
+  forked-session token replays are not double-counted, and sessions
+  predating token telemetry (Sept 2025) parse fine with zero cost.
+- **opencode**: child (subagent) sessions count toward tokens and tools
+  but not toward your prompt stats; opencode's own per-message cost is
+  used when present, otherwise the price table kicks in.
+
+## What gets covered in the meeting
+
+**You** get graded on clarity, patience, civility, and trust calibration:
+prompt lengths, a punch card of when you actually work, your late-night
+ratio, interrupt rate, vocabulary (including your "fix" count and your
+all-caps incidents), and the median seconds you give the agent before
+demanding more.
+
+**The agent** gets graded on efficiency, reliability, safety, and composure:
+"you're absolutely right" counts, apology rates, files it read 4+ times in
+one session (object permanence), retry storms (the same failing call, again,
+with hope), sensitive file touches with timestamps, blast radius, and its
+longest unsupervised tool-call chain.
+
+**The relationship** gets the rest: apology asymmetry, a timeline of your
+single longest session, an itemized Expense Report of Regret, compatibility
+score, and yearbook superlatives.
+
+Under the comedy there is a genuinely useful layer: sortable tables of
+redundant reads, retry storms, sensitive file touches, per-session cost
+trend, and top edited files. Real numbers, real receipts.
+
+## How the grading works
+
+Two report cards — one for the agent, one for you — plus an archetype, a
+compatibility score, and yearbook superlatives. None of it is vibes. Each
+grade is a weighted average of four traits, each trait a number from 0 to 1
+traced back to something you actually did:
+
+| who   | graded on (weights)                                          |
+|-------|--------------------------------------------------------------|
+| agent | efficiency (35%), reliability (30%), composure (20%), safety (15%) |
+| you   | clarity (30%), patience (30%), civility (20%), trust (20%)    |
+
+Two opinions are baked into the math worth flagging up front: there's such a
+thing as **too clear** (a 400-word prompt scores worse than an 80-word one),
+and **too trusting** (accepting every edit unread isn't trust, it's absence —
+the sweet spot is high, not maxed). Letter bands top out at A+ (≥0.93) and
+bottom out at D; there is no F.
+
+The full rubric — every formula, the six archetypes, the award thresholds, and
+why cost is an honest estimate — is written up in
+**[docs/scoring.md](docs/scoring.md)**. It is precise and it is not on your side.
+
+## Privacy
+
+Everything runs locally. The report is one HTML file with zero external
+requests: no CDN, no fonts, no analytics, no telemetry, no accounts.
+
+Don't take our word for it: **grep the source for `requests` or `urllib`.
+You will find nothing.** Then grep the generated HTML for `http`; you will
+find two footer links (this repo and the Repowise team) and nothing else.
+
+Roast mode is opt-in and sends **only aggregated numbers** (counts, ratios,
+the top-ten word list) to your own Claude account through your own `claude`
+CLI. No prompts, no code, no file paths leave your machine, ever.
+
+## Roast mode
+
+```bash
+skiplevel --roast
+```
+
+If the `claude` CLI is installed, the aggregated stats are sent to it with a
+60 second timeout, and three lines of the report (the manager's comment, the
+agent's review of you, and the share-card verdict) are written fresh for your
+specific numbers. On any failure it falls back silently to the built-in
+copy. Default mode never calls any LLM and is fully deterministic.
+
+## Sharing
+
+Built to be screenshotted. Every card grows copy and save buttons on
+hover: copy puts a PNG straight on your clipboard, save downloads it.
+The 1200x630 share card at the bottom has its own copy and save buttons,
+plus a GIF export that plays the whole review as a three-panel story —
+the two grades, then the agent's scorecard (its four traits and receipts),
+then yours (your traits, archetype, and verdict) — looped in the current
+theme (encoded in the page, no dependencies, nothing uploaded). Card export
+uses an inline SVG foreignObject render, which works in Chromium and Firefox;
+if your browser disagrees, the share card buttons are the reliable path.
+
+## How it works
+
+- Streams every transcript line, never loads files into memory, skips
+  anything malformed (and counts it). A multi-GB transcript directory takes
+  seconds. opencode's SQLite database is opened strictly read-only.
+- Harness-specific logic (scan paths, event normalization) lives behind a
+  small adapter interface: `adapters.py` (Claude Code + registry),
+  `adapter_codex.py`, `adapter_opencode.py`. Everything downstream is
+  harness-agnostic; tool names are normalized to one vocabulary so
+  "redundant reads" mean the same thing everywhere.
+- Deduplicates token usage by API message id (Claude Code writes one line per
+  content block, repeating the same usage object, which would otherwise
+  overcount cost by roughly 2.6x). Codex cumulative token counters are
+  converted to per-turn deltas, and the cached share of input is split out
+  before pricing.
+- Costs come from a hardcoded price table per model in `constants.py`, with
+  cache reads and writes priced separately (opencode's own recorded cost
+  wins when it has one). Flat-rate subscription usage is priced at API
+  rates, which is why the report calls it an estimate. Waste estimates
+  (re-reads, doomed retries) are labeled as estimates.
+- The grading rubric — traits, weights, bands, archetypes, awards, and the
+  waste/cost estimates — is documented in [docs/scoring.md](docs/scoring.md).
+- Schema notes from inspecting real transcripts live in
+  [docs/schema-notes.md](docs/schema-notes.md) (Claude Code),
+  [docs/schema-notes-codex.md](docs/schema-notes-codex.md), and
+  [docs/schema-notes-opencode.md](docs/schema-notes-opencode.md).
+
+## Roadmap
+
+- Per-agent comparison reviews (which of your reports earned the promotion)
+- Trend vs your last skip-level ("you interrupted 12% less this month. growth.")
+- More harnesses (Gemini CLI, Copilot CLI)
+
+## License
+
+MIT. Built by the [Repowise](https://github.com/repowise-dev/repowise) team.

skiplevel-1.1.0/README.md

@@ -0,0 +1,205 @@
+<div align="center">
+
+# skiplevel
+
+**Have a skip-level with your coding agents.**
+
+[![PyPI](https://img.shields.io/pypi/v/skiplevel?style=flat-square&logo=pypi&logoColor=white&label=pypi&color=6f54d6)](https://pypi.org/project/skiplevel/)
+[![Python](https://img.shields.io/pypi/pyversions/skiplevel?style=flat-square&logo=python&logoColor=white&color=4c8bf5)](https://pypi.org/project/skiplevel/)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue?style=flat-square)](LICENSE)
+[![Runs 100% local](https://img.shields.io/badge/runs-100%25_local-22c55e?style=flat-square)](#privacy)
+[![Agents](https://img.shields.io/badge/agents-Claude_Code_·_Codex_·_opencode-f59e0b?style=flat-square)](#supported-agents)
+
+<img src="https://raw.githubusercontent.com/repowise-dev/skiplevel/main/docs/hero.gif" alt="The 360 Review — a sample skiplevel report scrolling through the agent's scorecard" width="860">
+
+</div>
+
+You meet with the agent. The agent meets with you. Management hears both
+sides. skiplevel turns the transcripts already sitting on your machine
+into **The 360 Review**: a two-sided performance review between you and
+your coding agents — Claude Code, Codex CLI, and opencode. HR regrets
+scheduling the meeting.
+
+```
+$ uvx skiplevel
+
+skiplevel: scheduling a meeting with Claude Code + opencode's managers...
+  rifling through ~/.claude/projects ...
+  rifling through ~/.local/share/opencode ...
+  found 652 sessions (432 MB). Reading everything. Judging silently.
+  parsed 541 sessions across 31 days...
+  counted 52 'you're absolutely right's... oh no
+  tallied 34,849 tool calls and $4,062.61 in tokens...
+  found one file read 30 times in a single session. no further questions.
+  verdict: AGENT A- / YOU B. the committee has spoken.
+
+Skip-level complete in 8.1s. The truth is in skiplevel-report.html
+generated locally. nothing left your machine.
+```
+
+One self-contained HTML file. Four themes: midnight (dark, default),
+paper (printed HR document), terminal (green phosphor), and tabloid
+(newsprint gossip). Switchable from a pill in the report, persistent,
+and exports respect the active theme. Looks good in screenshots, which
+is the point.
+
+## Quickstart
+
+```bash
+uvx skiplevel          # zero install, zero config
+# or
+pip install skiplevel
+skiplevel
+```
+
+Flags:
+
+| flag        | what it does                                            |
+|-------------|---------------------------------------------------------|
+| `--harness H` | `auto` (default: review every agent with transcripts), `claude-code`, `codex`, or `opencode` |
+| `--dir PATH`  | transcripts root (default: each harness's own home)    |
+| `--out PATH`  | output file (default `./skiplevel-report.html`)        |
+| `--json`      | also dump the raw stats JSON next to the HTML          |
+| `--no-open`   | do not open a browser                                  |
+| `--roast`     | opt-in LLM roast via your own `claude` CLI (see below) |
+| `--theme T`   | initial theme: `midnight`, `paper`, `terminal`, `tabloid` |
+
+## Supported agents
+
+| harness     | where the diary lives                                       |
+|-------------|-------------------------------------------------------------|
+| Claude Code | `~/.claude/projects/**/*.jsonl`                             |
+| Codex CLI   | `$CODEX_HOME/sessions/` and `archived_sessions/` rollout JSONL (default `~/.codex`) |
+| opencode    | `~/.local/share/opencode/opencode.db` (SQLite), or the older `storage/` JSON tree |
+
+By default every harness with transcripts gets summoned into the same
+meeting and one combined review. `--harness codex` (or `claude-code`,
+`opencode`) reviews a single agent; `--dir` points at a non-standard
+location, and the layout is sniffed automatically.
+
+Notes per harness:
+
+- **Codex CLI**: archived copies of active sessions are deduplicated,
+  forked-session token replays are not double-counted, and sessions
+  predating token telemetry (Sept 2025) parse fine with zero cost.
+- **opencode**: child (subagent) sessions count toward tokens and tools
+  but not toward your prompt stats; opencode's own per-message cost is
+  used when present, otherwise the price table kicks in.
+
+## What gets covered in the meeting
+
+**You** get graded on clarity, patience, civility, and trust calibration:
+prompt lengths, a punch card of when you actually work, your late-night
+ratio, interrupt rate, vocabulary (including your "fix" count and your
+all-caps incidents), and the median seconds you give the agent before
+demanding more.
+
+**The agent** gets graded on efficiency, reliability, safety, and composure:
+"you're absolutely right" counts, apology rates, files it read 4+ times in
+one session (object permanence), retry storms (the same failing call, again,
+with hope), sensitive file touches with timestamps, blast radius, and its
+longest unsupervised tool-call chain.
+
+**The relationship** gets the rest: apology asymmetry, a timeline of your
+single longest session, an itemized Expense Report of Regret, compatibility
+score, and yearbook superlatives.
+
+Under the comedy there is a genuinely useful layer: sortable tables of
+redundant reads, retry storms, sensitive file touches, per-session cost
+trend, and top edited files. Real numbers, real receipts.
+
+## How the grading works
+
+Two report cards — one for the agent, one for you — plus an archetype, a
+compatibility score, and yearbook superlatives. None of it is vibes. Each
+grade is a weighted average of four traits, each trait a number from 0 to 1
+traced back to something you actually did:
+
+| who   | graded on (weights)                                          |
+|-------|--------------------------------------------------------------|
+| agent | efficiency (35%), reliability (30%), composure (20%), safety (15%) |
+| you   | clarity (30%), patience (30%), civility (20%), trust (20%)    |
+
+Two opinions are baked into the math worth flagging up front: there's such a
+thing as **too clear** (a 400-word prompt scores worse than an 80-word one),
+and **too trusting** (accepting every edit unread isn't trust, it's absence —
+the sweet spot is high, not maxed). Letter bands top out at A+ (≥0.93) and
+bottom out at D; there is no F.
+
+The full rubric — every formula, the six archetypes, the award thresholds, and
+why cost is an honest estimate — is written up in
+**[docs/scoring.md](docs/scoring.md)**. It is precise and it is not on your side.
+
+## Privacy
+
+Everything runs locally. The report is one HTML file with zero external
+requests: no CDN, no fonts, no analytics, no telemetry, no accounts.
+
+Don't take our word for it: **grep the source for `requests` or `urllib`.
+You will find nothing.** Then grep the generated HTML for `http`; you will
+find two footer links (this repo and the Repowise team) and nothing else.
+
+Roast mode is opt-in and sends **only aggregated numbers** (counts, ratios,
+the top-ten word list) to your own Claude account through your own `claude`
+CLI. No prompts, no code, no file paths leave your machine, ever.
+
+## Roast mode
+
+```bash
+skiplevel --roast
+```
+
+If the `claude` CLI is installed, the aggregated stats are sent to it with a
+60 second timeout, and three lines of the report (the manager's comment, the
+agent's review of you, and the share-card verdict) are written fresh for your
+specific numbers. On any failure it falls back silently to the built-in
+copy. Default mode never calls any LLM and is fully deterministic.
+
+## Sharing
+
+Built to be screenshotted. Every card grows copy and save buttons on
+hover: copy puts a PNG straight on your clipboard, save downloads it.
+The 1200x630 share card at the bottom has its own copy and save buttons,
+plus a GIF export that plays the whole review as a three-panel story —
+the two grades, then the agent's scorecard (its four traits and receipts),
+then yours (your traits, archetype, and verdict) — looped in the current
+theme (encoded in the page, no dependencies, nothing uploaded). Card export
+uses an inline SVG foreignObject render, which works in Chromium and Firefox;
+if your browser disagrees, the share card buttons are the reliable path.
+
+## How it works
+
+- Streams every transcript line, never loads files into memory, skips
+  anything malformed (and counts it). A multi-GB transcript directory takes
+  seconds. opencode's SQLite database is opened strictly read-only.
+- Harness-specific logic (scan paths, event normalization) lives behind a
+  small adapter interface: `adapters.py` (Claude Code + registry),
+  `adapter_codex.py`, `adapter_opencode.py`. Everything downstream is
+  harness-agnostic; tool names are normalized to one vocabulary so
+  "redundant reads" mean the same thing everywhere.
+- Deduplicates token usage by API message id (Claude Code writes one line per
+  content block, repeating the same usage object, which would otherwise
+  overcount cost by roughly 2.6x). Codex cumulative token counters are
+  converted to per-turn deltas, and the cached share of input is split out
+  before pricing.
+- Costs come from a hardcoded price table per model in `constants.py`, with
+  cache reads and writes priced separately (opencode's own recorded cost
+  wins when it has one). Flat-rate subscription usage is priced at API
+  rates, which is why the report calls it an estimate. Waste estimates
+  (re-reads, doomed retries) are labeled as estimates.
+- The grading rubric — traits, weights, bands, archetypes, awards, and the
+  waste/cost estimates — is documented in [docs/scoring.md](docs/scoring.md).
+- Schema notes from inspecting real transcripts live in
+  [docs/schema-notes.md](docs/schema-notes.md) (Claude Code),
+  [docs/schema-notes-codex.md](docs/schema-notes-codex.md), and
+  [docs/schema-notes-opencode.md](docs/schema-notes-opencode.md).
+
+## Roadmap
+
+- Per-agent comparison reviews (which of your reports earned the promotion)
+- Trend vs your last skip-level ("you interrupted 12% less this month. growth.")
+- More harnesses (Gemini CLI, Copilot CLI)
+
+## License
+
+MIT. Built by the [Repowise](https://github.com/repowise-dev/repowise) team.

skiplevel-1.1.0/pyproject.toml

@@ -0,0 +1,37 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "skiplevel"
+version = "1.1.0"
+description = "Have a skip-level with your coding agents: The 360 Review, a two-sided performance review generated locally from your own transcripts."
+readme = "README.md"
+license = "MIT"
+requires-python = ">=3.10"
+authors = [{ name = "Repowise" }]
+keywords = ["skiplevel", "claude", "claude-code", "codex", "opencode", "coding-agent", "analytics", "cli"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Environment :: Console",
+    "Topic :: Software Development",
+    "Operating System :: OS Independent",
+]
+dependencies = ["jinja2>=3.0"]
+
+[project.urls]
+Homepage = "https://github.com/repowise-dev/skiplevel"
+Issues = "https://github.com/repowise-dev/skiplevel/issues"
+
+[project.scripts]
+skiplevel = "skiplevel.cli:main"
+
+[tool.hatch.build.targets.wheel]
+packages = ["skiplevel"]
+
+[tool.hatch.build.targets.sdist]
+include = ["skiplevel", "README.md", "LICENSE"]

skiplevel-1.1.0/skiplevel/__init__.py

@@ -0,0 +1,3 @@
+"""skiplevel: The 360 Review for you and your coding agent."""
+
+__version__ = "1.1.0"