Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Abel-ai-lab/predict-anything --skill abel-investgit clone --depth 1 https://github.com/Abel-ai-lab/predict-anythingWrote 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/abel-ai-lab/predict-anything/abel-invest)<a href="https://agentmods.dev/skills/abel-ai-lab/predict-anything/abel-invest"><img src="https://agentmods.dev/badge/skills/abel-ai-lab/predict-anything/abel-invest/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/abel-ai-lab/predict-anything/abel-invest"><img src="https://agentmods.dev/badge/skills/abel-ai-lab/predict-anything/abel-invest.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 | $0.00143 | $0.03589 |
| Opus 5 | $0.00072 | $0.01795 |
| Sonnet 5 | $0.00029 | $0.00718 |
| Haiku 4.5 | $0.00014 | $0.00359 |
Grade A, and why
abel-invest 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 10d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- abel_invest/__init__.py 89 B runs code
- abel_invest/__main__.py 165 B runs code
- abel_invest/bootstrap_runtime_doctor.py 3.0 KB runs code
- abel_invest/cli.py 1.8 KB runs code
- abel_invest/narrative_core/__init__.py 82 B runs code
- abel_invest/narrative_core/cli_parser.py 14 KB runs code
- abel_invest/narrative_core/command_handlers/__init__.py 66 B runs code
- abel_invest/narrative_core/command_handlers/artifact_digest.py 22 KB runs code
- abel_invest/narrative_core/command_handlers/branch.py 47 KB runs code
- abel_invest/narrative_core/command_handlers/frontier.py 4.1 KB runs code
- abel_invest/narrative_core/command_handlers/session.py 8.1 KB runs code
- abel_invest/narrative_core/commands.py 3.9 KB runs code
- abel_invest/narrative_core/contracts/__init__.py 80 B runs code
- abel_invest/narrative_core/contracts/branch_spec.py 38 KB runs code
- abel_invest/narrative_core/contracts/constants.py 3.3 KB runs code
- abel_invest/narrative_core/contracts/graph_release.py 7.2 KB runs code
- abel_invest/narrative_core/contracts/paths.py 1.3 KB runs code
- abel_invest/narrative_core/contracts/templates.py 2.1 KB runs code
- abel_invest/narrative_core/dashboard_adapters/__init__.py 33 B runs code
- abel_invest/narrative_core/dashboard_payload.py 12 KB runs code
- abel_invest/narrative_core/dashboard.py 7.9 KB runs code
- abel_invest/narrative_core/evidence/__init__.py 71 B runs code
- abel_invest/narrative_core/evidence/evidence.py 26 KB runs code
- abel_invest/narrative_core/evidence/exploration_path.py 12 KB runs code
- abel_invest/narrative_core/evidence/frontier.py 31 KB runs code
- abel_invest/narrative_core/evidence/graph_frontier.py 26 KB runs code
- abel_invest/narrative_core/evidence/journal.py 8.5 KB runs code
- abel_invest/narrative_core/io.py 3.3 KB runs code
- abel_invest/narrative_core/promotion/__init__.py 1.7 KB runs code
- abel_invest/narrative_core/promotion/cleanup.py 615 B runs code
- abel_invest/narrative_core/promotion/constants.py 3.0 KB runs code
- abel_invest/narrative_core/promotion/facts.py 21 KB runs code
- abel_invest/narrative_core/promotion/gate.py 3.6 KB runs code
- abel_invest/narrative_core/promotion/models.py 1.3 KB runs code
- abel_invest/narrative_core/promotion/orchestrator.py 13 KB runs code
- abel_invest/narrative_core/promotion/packaging.py 11 KB runs code
- abel_invest/narrative_core/promotion/paper/__init__.py 95 B runs code
- abel_invest/narrative_core/promotion/paper/smoke.py 42 KB runs code
- abel_invest/narrative_core/promotion/paper/trace.py 11 KB runs code
- abel_invest/narrative_core/promotion/report.py 5.4 KB runs code
- abel_invest/narrative_core/promotion/request.py 31 KB runs code
- abel_invest/narrative_core/promotion/source_scan.py 22 KB runs code
- abel_invest/narrative_core/promotion/tail_oracle.py 7.4 KB runs code
- abel_invest/narrative_core/promotion/utils.py 3.7 KB runs code
- abel_invest/narrative_core/promotion/validation.py 17 KB runs code
- abel_invest/narrative_core/readiness.py 6.4 KB runs code
- abel_invest/narrative_core/rendering/__init__.py 68 B runs code
- abel_invest/narrative_core/rendering/renderers.py 27 KB runs code
- abel_invest/narrative_core/rendering/session_rendering.py 11 KB runs code
- abel_invest/narrative_core/runtime/__init__.py 76 B runs code
- abel_invest/narrative_core/runtime/context.py 25 KB runs code
- abel_invest/narrative_core/runtime/dsr_accounting.py 4.2 KB runs code
- abel_invest/narrative_core/runtime/edge_commands.py 3.8 KB runs code
- abel_invest/narrative_core/runtime/workflow_blockers.py 7.7 KB runs code
- abel_invest/narrative_core/sample_strategy_context.py 12 KB runs code
- abel_invest/narrative_core/session_lifecycle.py 17 KB runs code
- abel_invest/narrative_core/state.py 20 KB runs code
- abel_invest/narrative_core/strategy_artifact_upload.py 11 KB runs code
- abel_invest/narrative_core/strategy_artifacts.py 71 KB runs code
- abel_invest/narrative_core/strategy_sources.py 15 KB runs code
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.
- 10d ago First seen · 284 lines · 143 tokens per session scan A 83ffe88e48e3
abel-invest is a skill published in the GitHub repository Abel-ai-lab/predict-anything (19 stars, last pushed yesterday), with no licence file. It adds 143 tokens to every session and 3,589 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
connect-recommend
Use this skill when the user asks about Stripe Connect configuration, charge patterns, Dashboard access, or how to get started with Connect, is building a marketplace, platform, multi-vendor store, gig platform, or subscription platform, needs to pay out sellers, vendors, or providers, mentions split payments, revenue…
stripe-best-practices
Guides Stripe integration decisions across API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, tax and registrations (Stripe Tax, automatictax, product tax codes), Treasury financial accounts, integration options (Checkout, Payment…
tcx-brain
Author and manage TradingCodex Investment Brains. Use when the user asks to put principles or a Wiki insight into a Brain; create, inspect, revise, or validate a user-owned investment-brain- source; or install, update, activate, deactivate, roll back, or remove a managed Brain. Natural-language source authoring is…
tcx-strategy
Author and manage standalone Codex strategy skills named strategy- when the user wants an agent-readable investment strategy, library entry, entry or exit criteria, sizing rule, evidence standard, or decision-ready procedure. Start tool-using management with $tcx-strategy on the first meaningful line of a root turn…
tcx-memory
Review past investment decisions, run point-in-time historical replays, compare resolved forecasts and forward outcomes, and validate lesson candidates. Use when the user asks what happened before, why a thesis changed, whether a strategy lesson held out of sample, or what prior evidence is relevant to a current…
tcx-server
Operate TradingCodex server, read-only workspace viewer, MCP, update readiness, and broker connector status without build-turn or execution authority.