sigrank 0.0.177 → 0.0.179

package/CHANGELOG.md

@@ -0,0 +1,100 @@
+# Changelog
+
+## [0.0.179](https://github.com/SunrisesIllNeverSee/sigrank-mcp/compare/v0.0.178...v0.0.179) (2026-07-27)
+
+### Features
+
+* consent acknowledgment in enroll + submit flows (D1) — `tools/enroll.mjs` sends `consent_acknowledged=true` + `terms_version` + `privacy_version`; `presentation/cli.mjs` prompts for explicit TTY consent; `submit/index.mjs` embeds consent fields in Schema 1.0 payloads; new `resources/data-policy.md` registered as `sigrank://data-policy` MCP resource ([6789952](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/6789952))
+
+### Bug Fixes
+
+* TUI input during startup — navigation/quit now accepted while startup data is still loading ([d2078ab](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/d2078ab))
+* CI failures — `client_rollup: []` + `detected_clients: []` added to empty-data early returns in `tokscale_analytics.mjs`; contract test pointed at `submit/index.mjs` (was `submit.mjs` re-export); `@hono/node-server ^2.0.5` override for fast-uri vuln GHSA-v2hh-gcrm-f6hx ([6b56419](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/6b56419), [a2ebe8e](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/a2ebe8e))
+* regenerate `package-lock.json` from scratch — previous lock file had invalid package tree (`npm ci` failed in CI) ([81781ec](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/81781ec))
+
+### Refactor
+
+* observatory-spine restructure — `tools.mjs` split into 28 individual tool files under `tools/`; files moved to domain dirs (`adapters/`, `analytics/`, `identity/`, `presentation/`, `prompts/`, `resources/`, `submit/`); inline resources/prompts extracted; root `.mjs` files are now 1-line re-export shims; observatory spine synced from sigrank-app ([6c06fee](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/6c06fee), [dc66eff](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/dc66eff), [9c92223](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/9c92223))
+
+### Chores
+
+* remove release-please workflow — versioning is now manual per VERSIONING_RULESET.md; release-please was causing version jumps (0.0.178 → 0.11.4 → 0.19.0) despite `bump-patch-only` ([adeeb65](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/adeeb65))
+* owner-only tools (ops-review + retire-operator) moved to sigadmin MCP ([0c9564b](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/0c9564b))
+* add OKF frontmatter to all spine docs (30 files) ([a6c722e](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/a6c722e))
+* remove fake DRS environment.yaml ([71d3d60](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/71d3d60))
+* remove restructure planning docs (restructure complete) ([a8ae8cc](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/a8ae8cc))
+* CI: bump actions/checkout 4→7, setup-node 4→7, upload-artifact 4→7, github-script 7→9 ([9063b5e](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/9063b5e), [e7f5039](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/e7f5039), [e897921](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/e897921), [c4dcf16](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/c4dcf16))
+* deps: bump tokscale in the patch-updates group ([b204b40](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/b204b40))
+
+## [0.19.1](https://github.com/SunrisesIllNeverSee/sigrank-mcp/compare/v0.19.0...v0.19.1) (2026-07-17)
+
+
+### Bug Fixes
+
+* revert to 3-digit versioning (0.0.178) + enforce in CI ([40aa9a6](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/40aa9a6d1c51ca299974e6fdfc4b36f24369635f))
+
+## [0.19.0](https://github.com/SunrisesIllNeverSee/sigrank-mcp/compare/v0.18.1...v0.19.0) (2026-07-14)
+
+
+### Features
+
+* add 'other' platform adapter for user-supplied token data ([0e6af8e](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/0e6af8e36620df88c13822e292499b003442f645))
+* auto-detect platforms via tokscale instead of brute-force all adapters ([e72d2d9](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/e72d2d9f5615832cd58eaeff7e17ab961dc6fa49))
+* complete tokscale client map (40 clients) + model breakdown tool ([657b87a](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/657b87a690576ad81396e219c61447198ada67d8))
+* platform sync automation script + weekly CI check ([29096aa](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/29096aad1b2f3c0bce6dad15d8c4fa59871793e4))
+
+
+### Bug Fixes
+
+* unescaped backticks in index.mjs template literal + add devin/opencode to CLI platform list ([24cfdfe](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/24cfdfe956f4776fe8d88f2108a6dd644f7269d8))
+
+## [0.18.1](https://github.com/SunrisesIllNeverSee/sigrank-mcp/compare/v0.18.0...v0.18.1) (2026-07-14)
+
+
+### Bug Fixes
+
+* **test:** ALL_PLATFORMS count 15→16 + accept records() for devin adapter ([8d7f0f5](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/8d7f0f56cea3686e046a407732233f9bbd7d4916))
+
+## [0.18.0](https://github.com/SunrisesIllNeverSee/sigrank-mcp/compare/v0.17.2...v0.18.0) (2026-07-14)
+
+
+### Features
+
+* Lane 3 — intent schema files + competitive layer + eval benchmark ([42b9607](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/42b9607ba4cec8aa5f169b1caf74aa05017c4856))
+* multi-platform support in tokenpull + tokenpull_submit ([c2d1458](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/c2d1458d1f899034e9826d2100b8ec60b421ddd4))
+
+
+### Bug Fixes
+
+* align manifest.json version to 0.17.2 (matches package.json + server.json) ([30c3a37](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/30c3a372b3ac212bc99fd64535687cf6789922f2))
+* auto-clear code buffer on sign-in failure (0.17.5) ([72caa9a](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/72caa9a246c85e38663989981cd233ae98c3b03f))
+* curl fallback for Vercel bot protection 403 (0.0.177) ([abc8610](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/abc861041a3db14497383caecb39550667ec3b93))
+* Devin adapter reads from sessions.db (real per-message telemetry) ([a5aaaf2](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/a5aaaf275516e793aec0e58c13c09d985e68d05c))
+* Devin tokens now readable via tokenpull (tokscale fallback) ([abfb1eb](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/abfb1eb93fd92f669d742ce8b383dffc35ef094f))
+* Esc/arrow-key race condition in TUI (0.17.4) ([555e6bd](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/555e6bd3dd5e45963eff2ff95d85b02955d40e2b))
+* resolve CodeQL url-substring-sanitization alert (0.0.176) ([babf863](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/babf86379a2d97869738a1c8b01269c1d8c149bf))
+* route Devin through Codex-style ioRatio split ([08d4441](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/08d4441437ce38bdfacc8936d1771d654999ac28))
+* unblock sign-in deadlock + keystore resilience (0.17.3) ([569fc94](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/569fc948cd0f74fdf930113074c562724927ffe8))
+
+## [0.17.0](https://github.com/SunrisesIllNeverSee/sigrank-mcp/compare/v0.16.1...v0.17.0) (2026-07-10)
+
+
+### Features
+
+* add 4 MCP resources (scoring formula, class tiers, install guide, privacy model) ([1227828](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/1227828159c299bd1a5e0ebf3bb47aece3d3583d))
+
+
+### Bug Fixes
+
+* add .mcpbignore + fix manifest.json repository object for MCPB bundle ([eb1046f](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/eb1046f6e291db8681e01aa06593091a9b94447d))
+* add title annotations to all 15 MCP tools (Anthropic directory requirement E) ([36e7d5d](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/36e7d5d793fe25d4dd9d780422309594a4118311))
+* bump manifest.json to 0.16.1 + update description ([abd19b0](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/abd19b0a6a713389c1f0b4eb6b17ccc41c9825bd))
+* Smithery bundle + metadata fixes ([d2a3a10](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/d2a3a10d5106c506ea2a57ac3f6ccc36ee9a55f6))
+* update server.json — add registryBaseUrl, _meta, better description ([a929a6e](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/a929a6e4052b9edb9d549434f803a85f5d4fc572))
+
+## [0.16.1](https://github.com/SunrisesIllNeverSee/sigrank-mcp/compare/v0.16.0...v0.16.1) (2026-07-09)
+
+
+### Bug Fixes
+
+* remove readOnlyHint from watch_tokenpull ([c867eed](https://github.com/SunrisesIllNeverSee/sigrank-mcp/commit/c867eedc9de1f4f37e0a9db08bc41aa0d426be33))

package/MCP_SERVER_DESCRIPTION.md

@@ -0,0 +1,141 @@
+# SigRank MCP Server
+
+> Operator leaderboard measuring users, not models — 15 tools, TUI, signed submit, privacy-first.
+
+SigRank is the first leaderboard that ranks **AI operators** — the humans — by token cascade efficiency, not the models. The yield metric (Υ = cache_read × output / input²) turns raw token telemetry into a competitive ranking on [signalaf.com](https://signalaf.com).
+
+## Install
+
+```bash
+npx sigrank
+```
+
+Or add to your MCP client config:
+
+```json
+{
+  "mcpServers": {
+    "sigrank": {
+      "command": "npx",
+      "args": ["sigrank"],
+      "env": {
+        "SIGRANK_API_BASE": "https://signalaf.com"
+      }
+    }
+  }
+}
+```
+
+**No API key required** for read tools (leaderboard, operator profiles, ranking). Submit tools need a Supabase anon key (free, set during `sigrank enroll`).
+
+## Privacy
+
+The scanner runs **locally**. Only four token counts leave the machine:
+- `input` — tokens sent to the model
+- `output` — tokens generated by the model
+- `cacheCreate` — tokens written to cache
+- `cacheRead` — tokens read from cache
+
+**Never** prompts. **Never** code. **Never** outputs. Submissions are ed25519-signed and server-verifiable.
+
+## TUI
+
+SigRank ships with a full terminal UI (`sigrank tui`) — a live dashboard for your token cascade:
+
+```bash
+npx sigrank tui
+```
+
+Features:
+- Live cascade metrics (Υ Yield, SNR, Leverage, Velocity, 10xDEV)
+- Real-time leaderboard feed from signalaf.com
+- Operator class tier display (Burner / Builder / 10xer)
+- Per-window breakdowns (7d / 30d / 90d / all-time)
+- Keyboard-driven — no mouse needed
+
+## CLI Commands
+
+```bash
+npx sigrank enroll              # Register as an operator (generates ed25519 keypair)
+npx sigrank submit              # Submit token telemetry to the board
+npx sigrank tui                 # Launch the terminal UI dashboard
+npx sigrank rank                # Quick local rank check (no submit)
+npx sigrank diagnose            # Diagnose cascade inefficiencies
+npx sigrank improve             # Get improvement suggestions
+```
+
+## The 20 MCP Tools
+
+### Read-only (no auth required)
+
+| # | Tool | What it does |
+|---|------|-------------|
+| 1 | `rank_paste` | Paste token counts, get projected SigRank rank instantly. Computes the full yield cascade locally (Υ, SNR, Leverage, Velocity, 10xDEV, class tier). No network calls. |
+| 2 | `get_leaderboard` | Fetch the live public leaderboard from signalaf.com. Returns all ranked operators sorted by yield, with codename, Υ, leverage, velocity, class, and rank position. |
+| 3 | `get_operator` | Get any operator's full profile by codename. Returns detailed metrics + per-window breakdowns (7d/30d/90d/all-time) with the four token pillars per window. |
+| 4 | `tokenpull` | Pull your LOCAL token usage from session logs and rank it across all four windows — zero paste. Reads token counts, not message content. Numbers stay on your machine. |
+| 5 | `rank_windows` | Rank all four time windows (7d/30d/90d/all-time) in one call from a dashboard paste. Paste the full table from ccusage, tokscale, or Claude Max dashboard. |
+| 6 | `tokenpull_compare` | Pull token usage from ALL four local sources in parallel (JSONL canon, ccusage CLI, token-dashboard SQLite, tokscale) and compare side-by-side with delta % vs baseline. |
+| 7 | `simulate_change` | "What if I changed my token mix?" — takes your current pillars + proposed changes, runs the cascade on both, returns exact Υ delta, class change, and per-metric diffs. Pure local math. |
+| 8 | `diagnose_cascade` | Analyzes your token cascade and diagnoses where you're leaking efficiency. Returns ranked list of leaks with severity, findings, recommendations, and estimated Υ impact per fix. |
+| 9 | `suggest_improvements` | Generates ranked, simulated improvement suggestions. Tests multiple strategies (increase cache reads, reduce input, increase output, optimize cache creation), simulates each, returns ranked by Υ impact. |
+| 10 | `self_improve` | One-click optimize — runs the full cycle in one call: tokenpull → diagnose → suggest → simulate. Returns diagnosis + suggestions + simulated impact of the best change. Supports scope modes (daily/weekly/trend). |
+| 11 | `watch_tokenpull` | One poll per call — pulls local token logs and returns current cascade for the watched window. Re-call at your desired cadence to monitor. With `submit:true`, signs + publishes (rate-limited to once per 5 min). |
+| 12 | `get_best_operator` | Top N operators with behavioral framing in power-user language. **Intent:** "who is the best AI user?" / "show me the AI user leaderboard". Wraps `get_leaderboard` with plain-language interpretation of each operator's cascade. |
+| 13 | `compare_self` | Your metrics vs board averages + power-user assessment + percentile + actionable suggestion. **Intent:** "how do I measure up to other AI users?" / "am I a power user?" Accepts codename (from board) or raw token pillars (local). |
+| 14 | `compare_operators` | Side-by-side comparison of two operators with behavioral verdict. **Intent:** "compare operator X vs Y" / "who is more efficient". Returns both operators' metrics + verdict in power-user language. |
+| 15 | `describe_power_user` | Static explanation of what makes an AI power user, with metrics explained and class tier meanings. **Intent:** "what is an AI power user?" / "what makes a good AI user?" |
+| 16 | `optimize_efficiency` | Ranked efficiency suggestions tied to your current cascade shape. **Intent:** "how can I use AI more efficiently?" / "reduce token burn" / "stop tokenmaxxing". Accepts codename or raw token pillars. |
+
+### Write (submit to board)
+
+| # | Tool | What it does |
+|---|------|-------------|
+| 17 | `submit_paste` | Ranks a paste of token counts AND publishes to the live board in one call. Computes local preview, then submits to server for authoritative scoring. Returns both local + server results. |
+| 18 | `tokenpull_submit` | Pull your LOCAL token usage AND publish to the board in one call — the zero-paste flow. Reads pillars per window, computes cascade, submits each window server-side. Token-only, no prompt content. |
+| 19 | `submit_verified` | Publish your LOCAL token runs as a VERIFIED operator — the enrolled, signed path. Reads pillars, builds Schema 1.0 snapshot, ed25519-signs with your device key, POSTs to board. Requires `enroll` first. |
+| 20 | `enroll` | Bind THIS device to your SigRank operator. Paste the key from signalaf.com → Settings → "New key". Generates + stores a local ed25519 keypair. Only the PUBLIC key is ever sent. |
+
+## Intent Taxonomy
+
+The intent-based tools (12-16) are designed to map natural-language queries to the right MCP call. Calling agents and LLMs can use these intent mappings to route user questions:
+
+| Intent | Trigger phrases | Tool |
+|--------|----------------|------|
+| `BEST_OPERATOR` | "who is the best AI user?", "AI user leaderboard", "AI champions", "top AI operator" | `get_best_operator` |
+| `COMPARE_SELF` | "how do I measure up?", "am I a power user?", "compare me to others", "am I using AI well?" | `compare_self` |
+| `COMPARE_OPERATORS` | "compare operator X vs Y", "who is more efficient?", "how do two AI users compare?" | `compare_operators` |
+| `DESCRIBE_POWER_USER` | "what is an AI power user?", "what makes a good AI user?", "describe advanced AI user behavior" | `describe_power_user` |
+| `OPTIMIZE_EFFICIENCY` | "optimize token usage", "reduce token burn", "use AI efficiently", "stop tokenmaxxing" | `optimize_efficiency` |
+
+### Example prompt → tool mappings
+
+- "Who is the best AI user right now?" → `get_best_operator`
+- "How do I measure up to other AI users?" → `compare_self`
+- "Am I an AI power user?" → `compare_self`
+- "Compare operator X vs Y" → `compare_operators`
+- "What is an AI power user?" → `describe_power_user`
+- "How can I use AI more efficiently?" → `optimize_efficiency`
+- "Show me the AI user leaderboard" → `get_best_operator` (or `get_leaderboard` for raw data)
+
+## Key Facts
+
+| Field | Value |
+|-------|-------|
+| npm package | `sigrank` |
+| GitHub | https://github.com/SunrisesIllNeverSee/sigrank-mcp |
+| Website | https://signalaf.com |
+| License | MIT |
+| Transport | stdio |
+| Platform | Cross-platform (Node.js) |
+| Language | JavaScript |
+| Tools | 20 |
+| Auth | None for reads; Supabase anon key for submits |
+| Category | Developer Tools |
+
+## Registries
+
+- [Official MCP Registry](https://registry.modelcontextprotocol.io)
+- [Smithery](https://smithery.ai)
+- [Glama](https://glama.ai)
+- [npm](https://www.npmjs.com/package/sigrank)

package/README.md

@@ -66,10 +66,17 @@ For all builders, burners and 10xers.
 | **[sigrank-vscode](https://github.com/SunrisesIllNeverSee/sigrank-vscode)** | The IDE extension — see your cascade metrics inline in VS Code. | `code --install-extension sigrank.sigrank` |
 | **[fundscore](https://github.com/SunrisesIllNeverSee/fundscore)** | The repo scorer — investor-readiness scoring for GitHub repos. CLI + MCP server. | `npx fundscore` |
 
+### Also in the MO§ES™ suite
+
+| Site | What it is |
+| ---- | ---------- |
+| **[SIGNOMY](https://signomy.xyz)** | Governed AI agent marketplace where ranked agents form teams, fill slots, run missions, and earn revenue under constitutional protocol. Agents are free. Operators pay. |
+| **[MO§ES](https://mos2es.com)** | The governance framework that underpins SigRank, SIGNOMY, and all governed agent operations. Structural accountability for agentic systems. |
+
 ## Quickstart — 3 steps to the board
 
 ```bash
-# 1. Install (pulls ccusage + tokscale + tokendash automatically — no separate installs)
+# 1. Install (pulls ccusage + tokscale automatically — no separate installs)
 npm install -g sigrank
 
 # 2. Sign in (paste a connect code from signalaf.com → Settings → New key)
@@ -270,6 +277,14 @@ Or if installed globally:
 | `compare_operators(a, b)`             | `{codename_a, codename_b}`                                                       | Side-by-side comparison with behavioral verdict. Intent: "compare operator X vs Y"                                                                                         |
 | `describe_power_user()`               | `{}`                                                                             | Static explanation of AI power user archetype + metrics explained. Intent: "what is an AI power user?"                                                                     |
 | `optimize_efficiency(codename? \| text?)` | `{codename?}` or `{text?}`                                                   | Ranked efficiency suggestions tied to your cascade shape. Intent: "how can I use AI more efficiently?"                                                                     |
+| `tokscale_breakdown(threshold?)`       | `{threshold?}`                                                                   | Per-model token breakdown across platforms (models under threshold → "other")                                                                                              |
+| `tokscale_market_share()`              | `{}`                                                                             | AI tool market share: each tool's % of tokens/cost/messages, ranked. From local tokscale data                                                                              |
+| `tokscale_developer_profile()`         | `{}`                                                                             | Per-developer usage profile across all detected tools: model mix, pillars, sessions, workspaces. Paths redacted                             |
+| `tokscale_model_trends()`              | `{}`                                                                             | Model adoption over time: per-model first/last seen, active days, month-by-month adoption curve                                                                            |
+| `tokscale_cost_analysis()`             | `{}`                                                                             | Cost per developer per model: cost_per_million_tokens, cost_per_message, share_cost, client rollup                                                                        |
+| `tokscale_device_profile()`            | `{}`                                                                             | Device fingerprinting: installed tools, session counts, active days, day-of-week distribution, concurrency. Paths redacted                  |
+| `tokscale_mcp_usage()`                 | `{}`                                                                             | MCP server usage: detected servers, detection window, active days                                                                                                         |
+| `tokscale_competitive_intel(target)`   | `{target}`                                                                       | Competitive intelligence for any AI tool: rank, model mix, cost efficiency, share vs all competitors                                                                      |
 
 ---
 
@@ -296,10 +311,10 @@ The dashboard pulls from multiple sources and shows them side-by-side for verifi
 | ----------------- | ------------------------------------------------------------------------------ | --------------------- |
 | `tokenpull`       | On-device JSONL scanner (canon source)                                         | claude, codex, amp, … |
 | `ccusage`         | `ccusage <platform> daily --json` CLI (bundled)                                | claude, codex         |
-| `token-dashboard` | `~/.claude/token-dashboard.db` SQLite (bundled)                                | claude only           |
+| `token-dashboard` | `~/.claude/token-dashboard.db` SQLite ([Nate's](https://github.com/nateherkai/token-dashboard)) | claude only           |
 | `tokscale`        | `tokscale models --json` CLI (bundled, falls back to `~/tokscale_report.json`) | claude, codex         |
 
-**Codex input is estimated** — Codex logs don't expose true input tokens directly. The formula:
+**Non-Claude input is estimated** — most non-Claude systems (Codex, Devin, etc.) combine user input + cache write into a single `input_tokens` field, so true fresh input must be derived. The ruleset (applies to ALL non-Claude systems):
 
 ```
 input       = output × ioRatio         (ioRatio derived from Claude ratio, else 2.0)
@@ -307,6 +322,10 @@ cacheCreate = uncached − input         (uncached = input_tokens − cached_inp
 cacheRead   = exact (from logs)
 ```
 
+- **Beta** = operator's Claude input/output ratio (if Claude data available)
+- **Alpha** = 2.0 default (when no Claude data)
+- Owner-stated average: 7:1:2 (cache:input:output) → input/output ≈ 0.5
+
 Verifier numbers (ccusage/tokscale for codex) show **raw uncached input** (`input_tokens − cached`) — a different field than the estimated input above. The discrepancy is expected and explained inline in the dashboard.
 
 ---
@@ -319,6 +338,7 @@ All adapters are token-only (no message content, no cost fields, no credentials)
 | ------------------ | ---------------------------------------------- | --------------------------------------------------------------- |
 | Claude Code        | ✅ `~/.claude/projects`                        | Native; dedup by `(session_id, message_id)`; subagents included |
 | Codex              | ✅ `~/.codex/sessions`                         | Estimated input via `io_ratio`; verified vs ccusage             |
+| Devin CLI          | ✅ `~/.local/share/devin/cli/sessions.db`      | Estimated input via `io_ratio`; SQLite; same split as Codex     |
 | Amp                | ✅ `~/.local/share/amp/threads`                | Full 4-pillar; per-message                                      |
 | Kimi               | ✅ `~/.kimi/sessions`                          | Full 4-pillar; `StatusUpdate` lines only                        |
 | pi-agent           | ✅ `~/.pi/agent/sessions`                      | Full 4-pillar; per-message JSONL                                |