--- name: pp-screener description: "Every Screener.in feature, plus offline search, screen intersections, and a local fundamentals mirror no other tool has. Trigger phrases: `check fundamentals for INFY`, `run the bull cartel screen`, `who's buying insider stock this month`, `compare TCS and Wipro`, `latest quarterly results`, `screener data`, `use screener.in`." author: "Som Samantray" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - screener-pp-cli install: - kind: go bins: [screener-pp-cli] module: github.com/mvanhorn/printing-press-library/library/other/screener/cmd/screener-pp-cli --- # Screener.in — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `screener-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first: 1. Install via the Printing Press installer. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install screener --cli-only ``` 2. Verify: `screener-pp-cli --version` 3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill. If the `npx` install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.5 or newer). This installs into `$GOPATH/bin` (default `$HOME/go/bin`), so add that directory to `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/other/screener/cmd/screener-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. Search any Indian company and pull its full fundamental profile — key metrics, machine-generated pros/cons, quarterly results, P&L, balance sheet, cash flow, ratios, shareholding, peers, and price charts — from the terminal. Sync company pages, screens, and insider trades into a local SQLite mirror, then run cross-company comparisons, quarterly trend flags, screen overlaps, and insider-flow rankings that no single page or API call provides. ## When to Use This CLI Use this CLI for Indian equity fundamental research: checking a company's full profile, screening the market by a strategy, comparing candidates, monitoring quarterly earnings trends, tracking insider activity, and building a local fundamentals mirror for offline or agent-driven analysis. ## Anti-triggers Do not use this CLI for: - Do not use for intraday price action or live quotes — Screener.in data updates at market close, not real time - Do not use for option chain or derivatives data — Screener.in covers equities only - Do not use for US or non-Indian markets — Screener.in covers NSE/BSE listed companies ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Local state that compounds - **`compare`** — See two to four companies' fundamentals side by side (valuation, margins, growth, insider activity) without tab-switching. _Pick this when an agent needs to decide between candidate stocks on comparable fundamentals instead of fetching pages one at a time._ ```bash screener-pp-cli compare TCS HDFCBANK --agent ``` - **`qtrend`** — Spot whether a company's quarterly profit/sales growth is accelerating or deteriorating, with YOY change and margin drift computed automatically. _Pick this when an agent needs the trend shape of a company's earnings, not just the latest quarter's raw numbers._ ```bash screener-pp-cli qtrend INFY --quarters 8 --agent ``` - **`insider-flow`** — Answer 'who is net buying the most this month?' with per-company insider buy/sell aggregation. _Pick this when an agent needs insider conviction ranked by net value, not a raw list of individual trades._ ```bash screener-pp-cli insider-flow --since 30d --top 10 --agent ``` ### Cross-entity local queries - **`overlap`** — Find companies that appear in two or more stock screens in one command, replacing spreadsheet dedup. _Pick this when an agent needs the intersection of multiple screening strategies to find high-conviction candidates._ ```bash screener-pp-cli overlap 1 the-bull-cartel 59 magic-formula --agent ``` - **`rank`** — Re-score a screen's companies with a composite of fundamentals (P/E, ROCE, growth), sorted by what matters to you. _Pick this when an agent should prioritize within a screen by fundamentals or insider conviction rather than the default table order._ ```bash screener-pp-cli rank 1 the-bull-cartel --by roce --agent ``` ## Command Reference **company** — Search companies and fetch fundamental profiles - `screener-pp-cli company by-id` — Fetch a company page by numeric ID (redirects to symbol page) - `screener-pp-cli company chart` — Fetch price/technical chart data for a company - `screener-pp-cli company peers` — Fetch peer comparison table for a company - `screener-pp-cli company profile` — Fetch the full company profile page (key metrics, analysis, quarterly results, P&L, balance sheet, cash flow, ratios - `screener-pp-cli company profile-standalone` — Fetch standalone (parent-only) company profile page - `screener-pp-cli company search` — Search for companies by name or ticker (live autocomplete API) **explore** — Browse popular screens and sector categories - `screener-pp-cli explore` — Browse popular themes, formulas, and sector categories **filings** — Market pulse filings hub (requires login) - `screener-pp-cli filings` — Market Pulse hub: bulk deals, block deals, SAST trades, insider trades **full_text_search** — Full-text search across companies and filings (requires login) - `screener-pp-cli full-text-search` — Full-text search for companies **ipo** — Upcoming and recent IPO listings - `screener-pp-cli ipo` — List upcoming IPOs with subscription status **market** — Browse market sectors and industry groups - `screener-pp-cli market ` — List companies in a market sector (e.g. IN08/IN0801/IN080101 = IT - Software) **results** — Latest quarterly results (Market Pulse, requires login) - `screener-pp-cli results` — Latest quarterly results with YOY growth (Sales, EBIDT, Net profit, EPS) and filters **screens** — Browse and run stock screening screens - `screener-pp-cli screens list` — List all stock screening screens - `screener-pp-cli screens run` — Run a stock screen and get ranked results (CMP, P/E, Mar Cap, Div Yld, NP Qtr, Qtr Profit Var, Sales Qtr, Qtr Sales Var **trades** — Market pulse trade activity (requires login) - `screener-pp-cli trades` — Insider trades (bought/sold/pledge/ESOP) with filters ## Freshness Contract This printed CLI owns bounded freshness only for registered store-backed read command paths. In `--data-source auto` mode, those paths check `sync_state` and may run a bounded refresh before reading local data. `--data-source local` never refreshes. `--data-source live` reads the API and does not mutate the local store. Set `SCREENER_NO_AUTO_REFRESH=1` to skip the freshness hook without changing source selection. Covered paths: - `screener-pp-cli explore` - `screener-pp-cli explore get` - `screener-pp-cli explore list` - `screener-pp-cli explore search` - `screener-pp-cli filings` - `screener-pp-cli filings get` - `screener-pp-cli filings list` - `screener-pp-cli filings search` - `screener-pp-cli full_text_search` - `screener-pp-cli full_text_search get` - `screener-pp-cli full_text_search list` - `screener-pp-cli full_text_search search` - `screener-pp-cli ipo` - `screener-pp-cli ipo get` - `screener-pp-cli ipo list` - `screener-pp-cli ipo search` - `screener-pp-cli screens` - `screener-pp-cli screens get` - `screener-pp-cli screens list` - `screener-pp-cli screens search` When JSON output uses the generated provenance envelope, freshness metadata appears at `meta.freshness`. Treat it as current-cache freshness for the covered command path, not a guarantee of complete historical backfill or API-specific enrichment. ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash screener-pp-cli which "" ``` `which` resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code `0` means at least one match; exit code `2` means no confident match — fall back to `--help` or use a narrower query. ## Recipes ### Full company research brief ```bash screener-pp-cli company profile RELIANCE --agent --select top_ratios,analysis,quarterly_results ``` One command returns the key metrics, pros/cons, and quarterly results as agent-ready JSON ### High-conviction screen intersection ```bash screener-pp-cli overlap 1 the-bull-cartel 59 magic-formula --agent ``` Companies passing both a value formula and a growth screen ### Insider conviction ranking ```bash screener-pp-cli insider-flow --since 30d --top 10 --agent ``` Who's net buying the most this month, ranked by value ### Earnings momentum check ```bash screener-pp-cli qtrend INFY --quarters 8 --agent ``` Is profit growth accelerating or deteriorating over 8 quarters? ### Candidate shortlist comparison ```bash screener-pp-cli compare TCS WIPRO HCLTECH --agent --select name,pe,roce,profit_growth ``` Side-by-side fundamentals for a shortlist, narrowed with --select ## Auth Setup Screener.in's public pages (company profiles, screens, sectors, IPO) need no login. Market-pulse pages — latest quarterly results, insider trades, filings — require a free Screener.in account. Run 'screener-pp-cli auth login --chrome' to import your logged-in Chrome session cookie once; the CLI replays it for gated pages. Run `screener-pp-cli doctor` to verify setup. ## Agent Mode Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color --yes`. - **Pipeable** — JSON on stdout, errors on stderr - **Filterable** — `--select` keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs: ```bash screener-pp-cli company search --q example-value --agent --select id,name,url ``` - **Previewable** — `--dry-run` shows the request without sending - **Offline-friendly** — sync/search commands can use the local SQLite store when available - **Non-interactive** — never prompts, every input is a flag - **Read-only** — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests ### Response envelope Commands that read from the local store or the API wrap output in a provenance envelope: ```json { "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."}, "results": } ``` Parse `.results` for data and `.meta.source` to know whether it's live or local. A human-readable `N results (live)` summary is printed to stderr only when stdout is a terminal AND no machine-format flag (`--json`, `--csv`, `--compact`, `--quiet`, `--plain`, `--select`) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout. ## Paths and state Agents should treat the CLI's path resolver as part of the runtime contract: - Use `--home ` for one invocation, or set `SCREENER_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `SCREENER_CONFIG_DIR`, `SCREENER_DATA_DIR`, `SCREENER_STATE_DIR`, `SCREENER_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `SCREENER_HOME`, XDG (`XDG_CONFIG_HOME`, `XDG_DATA_HOME`, `XDG_STATE_HOME`, `XDG_CACHE_HOME`), then platform defaults. - `config` contains settings like `config.toml` and profiles. `data` contains `credentials.toml`, `data.db`, cookies, and auth sidecars. `state` contains persisted queries, jobs, and `teach.log`. `cache` contains regenerable HTTP/cache files. - Stored secrets live in `credentials.toml` under the data dir. Existing legacy `config.toml` secrets are read for compatibility and leave `config.toml` on the first auth write. - Run `screener-pp-cli doctor --fail-on warn` to surface path and credential-location warnings. `agent-context` exposes a schema v4 `paths` block for agents that need the resolved dirs. - For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags: ```json { "mcpServers": { "screener": { "command": "screener-pp-mcp", "env": { "SCREENER_HOME": "/srv/screener" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `SCREENER_HOME` or per-kind vars as durable fleet levers, and use `--home` only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing `SCREENER_HOME`, or `doctor` will not find credentials left under the former root. ## Automatic learning This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a `flag_alias` candidate, and a `teach` on a query family without a playbook auto-synthesizes a `playbook_candidate` from the session's journal. Your job is judgment only: `recall` first, act on surfaced candidates, `teach` the final answer, `playbook amend` when you observe a correction. You never record failures by hand. ### Step 1: `recall` before any discovery Before list/search/drill commands on a new user question, run: ```bash screener-pp-cli recall "" --agent ``` The response envelope: ```json { "query": "...", "normalized": "", "query_entities": ["..."], "found": true | false, "match_score": 0.0, "results": [ { "resource_id": "...", "resource_type": "...", "venue": "...", "confidence": 2, "entity_match": "exact|partial|unknown", "source": "taught|preseed|pattern", "warnings": ["..."] } ], "mismatches": [ /* only when --debug-mismatches */ ], "warnings": [ /* top-level */ ], "candidates": [ { "id": 12, "class": "flag_alias | playbook_candidate", "summary": "...", "sightings": 3, "last_seen": "...", "rationale": "...", "next_action": ["", "screener-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "", "purpose": "..." } ], "entity_slots": ["$ENTITY"], "expected_tool_calls": 3 }, "slots_resolved": { "$ENTITY": { "token": "", "canonical": "" } }, "notes": "" }, "notes": "" } ``` Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and `learnings list` and `learnings candidates` are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught. ### Step 2: decision tree Read `candidates`, `playbook`, `notes`, `results[0]`, and warnings in that order: ``` if Candidates present (warnings include "candidates_present"): -> candidates are try-then-confirm, never facts. Follow each candidate's two-step next_action verbatim: run the trial command first, then run `learnings confirm ` only after the trial verified the behavior. Reject a wrong candidate with `learnings reject `. -> NEVER re-teach something recall surfaced as a candidate; confirm or reject that candidate instead of teaching a duplicate. -> candidates ride alongside playbooks and resource hits, not instead of them; continue with the branches below after acting on them. if Playbook present: -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose) -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries for the entity slot tokens. If a step's slot is unresolved, fall back to discovery for that step only. -> the Playbook's expected_tool_calls is a budget; if you find yourself running materially more, record the divergence via `screener-pp-cli playbook amend` at end-of-session. elif Notes present (no Playbook): -> read Notes verbatim before any discovery step; they carry known gotchas for this query family even when no structured choreography exists yet. elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2: -> skip discovery; fetch live data for Results[*].ResourceID in parallel elif Found AND Results[0].EntityMatch == "partial": -> candidate hint, NOT a hit; read the resource title to validate before trusting elif (any row in Mismatches[] when --debug-mismatches was passed): -> treat as cold start; the stored learning is for a different entity (different canonical resolved from query_entities) else: // Found == false, no playbook, no notes -> cold start; run discovery normally; teach the answer afterward (Step 4). If the family has no playbook yet, that teach auto-synthesizes a playbook candidate from this session's journal - you do not need to record one by hand. ``` Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a `Results[]` hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping `mismatches`; pass `--debug-mismatches` only when investigating cold-start surprises. Candidate judgment details: `learnings confirm ` prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. `learnings reject ` tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; `screener-pp-cli learnings candidates` lists the full open set. Graceful degradation: if `learnings confirm` is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol. ### Step 3: always read `warnings` - `low_confidence`: row exists at `confidence<2`. Treat as a hint, not a skip-discovery hit. - `resource_not_in_store`: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate. - `cross_alias_match` (per-result): the row was taught under a different alias and matched the live query's canonical via `entity_lookups` (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id. - `similar_shape_different_entity:` (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results. - `ambiguous_alias` (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource. - `candidates_present` (top-level): the envelope carries a `candidates` section. Handle