Borrowing it
Nothing to install: this file belongs to Kemetra/Seshat-BI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Kemetra/Seshat-BI/main/.claude/skills/portfolio-watch/SKILL.mdgit clone --depth 1 https://github.com/Kemetra/Seshat-BIWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kemetra/seshat-bi/portfolio-watch)<a href="https://agentmods.dev/skills/kemetra/seshat-bi/portfolio-watch"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/portfolio-watch/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kemetra/seshat-bi/portfolio-watch"><img src="https://agentmods.dev/badge/skills/kemetra/seshat-bi/portfolio-watch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00210 | $0.02073 |
| Opus 5 | $0.00105 | $0.01037 |
| Sonnet 5 | $0.00042 | $0.00415 |
| Haiku 4.5 | $0.00021 | $0.00207 |
Grade A, and why
portfolio-watch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
portfolio-watch
Portfolio Watch answers one recurring question: since we last looked, what changed,
what still needs a human, and what is the one next thing to do per scope? It is the
baseline-diffable, multi-dimension EXTENSION of the point-in-time retail-control-room
roll-up (F012) -- same read-only, aggregate-never-re-derive posture, plus a persisted
snapshot and the drift/semantic-drift/dashboard-intent-divergence dimensions the control
room does not fold in.
Scope wall (read first)
- Aggregates, never re-derives. Every finding is sourced from a shipped surface's
already-committed output (
drift.py/drift_semantics.py,metric_drift.py,semantic_audit.py/report_intent.py,readiness_projection.py/readiness_classify.py,approval_inbox.py,review_integration.py/review_pack_export.py). It runs NO new check and calls NONE of those surfaces' own comparators itself -- it reads what they already recorded and cites the path. - No new gate / rule / approval mechanism. This is a Tier-5 read/summarize/derive
companion (roadmap binding rule), not another governance engine.
seshat check's rule inventory and exit behavior are unchanged by this skill's existence. - No score, ever. Only the four readiness spine statuses, the shipped categorical finding enums (relayed verbatim), and measured magnitudes (counts/rates/deltas) traced to a committed source appear anywhere. A health/confidence/priority/quality number is never emitted (hard rule #9) -- if asked for one, decline and point here.
- No live database in the MVP. The governed-scope set comes from committed
mappings/*/readiness-status.yamlpaths (the same setstatus_surface/readiness_projectionalready track), never a live metadata query. A dimension whose evidence needs a live re-profile with no DSN configured is truthfully[PENDING LIVE]. - Relays Principle-V, decides none of it. A grain/PII/returns/rollup/identity/approval
condition is relayed with a named owner; this skill originates no ruling on any of them.
requires_human_attentionfires independently of category rank whenever an unmet approval or a relayed Principle-V/PII drift blocker is present -- it can never be buried by a higher-ranked, less dangerous condition. - "Recurring" = re-runnable + baseline-diffable, not a scheduler. There is no cron, no hosted monitoring, no continuous-run surface here or planned by this skill.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 141 lines · 210 tokens per session scan A c57d0c55a5ef
portfolio-watch is a skill published in the GitHub repository Kemetra/Seshat-BI (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 210 tokens to every session and 2,073 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ktx-analytics
Use when answering a question that needs data from a ktx-connected database - investigating, analyzing, "how many", "show me", "what's the breakdown of", finding records by value, exploring tables, comparing periods, explaining metrics, or any data-analysis request. Triggers even when the user does not say…
metabase_ingest
Convert Metabase questions, models, and metrics into ktx Semantic Layer source definitions. Covers result-metadata to KSL column type mapping, FK/PK detection, near-duplicate deduplication, pre-aggregation decomposition, join-graph connectivity, and how to react to priorProvenance from earlier ingest syncs. Load when…
sl_capture
How to capture new reusable patterns into ktx's semantic layer - when a measure, segment, or join belongs in the catalog and how to write it generically so it stays small and useful over time. Loaded by the post-turn memory-agent only. The research agent does not write to the SL.
looker_ingest
Extract durable ktx knowledge and semantic-layer contribution proposals from staged Looker runtime dashboard, Look, and explore JSON. Load for WorkUnits whose raw files are under explores/, dashboards/, or looks/.
metricflow_ingest
Map a MetricFlow semanticmodel or metric into ktx semantic layer sources. Covers the MetricFlow to ktx primitive table, extends: inheritance flattening, metric-type handling (simple / derived / ratio / cumulative / conversion), model: ref('x') resolution, and four worked examples. Load when the turn contains…
lookml_ingest
Map a LookML view/model/explore into ktx semantic layer sources. Covers the LookML to ktx primitive table, provenance tagging, and three worked examples (overlay, standalone from derivedtable, standalone with sqlalwayswhere). Load when the turn contains .lkml content.