Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/agentii-ai/agentii-investment-intelligencenpx agentmods add skills/agentii-ai/agentii-investment-intelligence/challengeWrote 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/agentii-ai/agentii-investment-intelligence/challenge)<a href="https://agentmods.dev/skills/agentii-ai/agentii-investment-intelligence/challenge"><img src="https://agentmods.dev/badge/skills/agentii-ai/agentii-investment-intelligence/challenge/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/agentii-ai/agentii-investment-intelligence/challenge"><img src="https://agentmods.dev/badge/skills/agentii-ai/agentii-investment-intelligence/challenge.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 | $0.00101 | $0.00557 |
| Opus 5 | $0.00051 | $0.00279 |
| Sonnet 5 | $0.00020 | $0.00111 |
| Haiku 4.5 | $0.00010 | $0.00056 |
Grade A, and why
challenge 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 yesterday.
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.
What it actually says
agentii.challenge
The buyer-side IC verb: challenge the thesis. Not audit — that name was taken
three times (audit-xls, quality-audit.yaml, G3) — challenge is the thing that
happens in an investment committee.
Method bodies (the four angles)
- Cross-run contradiction — the entity index (
reduce_journals.build_entity_index): same(entity, metric, period)with different values. Sameretrieved_at→ true contradiction; different → suspected restatement. The validator never auto-resolves — candidates go to the IC agenda. - Pre-mortem — assume the loss already happened; reconstruct the path backwards. Which pillar failed first? What data would have to be wrong?
- Inversion — what would make this thesis a sell? What would the bear's best case look like? What would falsify the conviction, not just the claim?
wrong_iffalsifiability — is each falsifier mechanically checkable (metric + threshold + source)? A prose falsifier is not a falsifier (Q8-4).
Economics (Q40/Q68)
- Findings: ≈50 cap, severity-sorted; overflow aggregates by category.
- Finding IDs are content-derived (
hash(entity+metric+period+gap_type)) — unchanged re-runs yield byte-identical IDs (eval corpus comparability). - Scope is incremental (artifacts whose pins/
as_ofchanged since last run) with three backstops: every Nth converge / constitution MINOR-MAJOR / subscription change (new subscriptions create new comparison pairs — Q9). - Lifecycle hooks: pillar-complete (cheap, early) / thesis-complete (final line) / pre-reduction (claims entering the portfolio are adversarially verified). Unchallenged claims never enter the knowledge base (Q64).
Invocation
python3 scripts/challenge.py --nth-converge 10
What ships with it
1 file 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.
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.
- yesterday First seen · 44 lines · 101 tokens per session scan A 1d52dfe6a309
challenge is a skill published in the GitHub repository agentii-ai/agentii-investment-intelligence (204 stars, last pushed today), licensed Apache-2.0. It adds 101 tokens to every session and 557 once invoked, about $0.0005 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 2026-09-09.
Other skills, from other repositories
deal-packet
Produce the full institutional deal packet for a deal — Excel underwriting model + Word IC memo + PowerPoint deck + PDF one-pager — all Bristol-branded, fully cited, and cross-linked to one sources registry. Use when the user says "build the packet," "full workup," "put together the IC package," "model this deal," or…
deal-memo
Assemble research into a polished investment committee memo, market study, or deal one-pager. Use when the user says "write the memo," "put together an IC memo," "make a one-pager," "turn this into a document for the committee/lenders/LPs," or wants research packaged into a deliverable.
deal-pipeline
Track deals across stages and produce status updates. Use when the user says "track this deal," "what's in my pipeline," "update the status on [deal]," "give me a pipeline summary," or wants an overview of what's moving.
investor-sourcing
Research capital partners and LPs for a raise, and research who owns or controls a parcel or entity and how to contact them. Use when the user says "find investors," "who could fund this," "research this capital partner," "who owns this land/parcel," "who's behind this LLC," or needs investor/owner background and…
market-comp-analysis
Pull rent comps, occupancy, supply pipeline, absorption, and cap-rate trends for a submarket, then build a market study. Use when the user asks for "comps," "rent comps," "market study," "what are rents doing," "cap rates," "what's the competition," or needs the market picture behind a deal.
underwriting-research
Research the real-world assumptions behind a multifamily underwriting model — achievable rents, operating expenses, taxes, insurance, construction/hard costs, and available incentives. Use when the user says "check my assumptions," "what should I underwrite for," "research expenses/taxes/insurance/construction costs,"…